{"id":42323,"date":"2023-05-06T16:39:33","date_gmt":"2023-05-06T08:39:33","guid":{"rendered":"https:\/\/swarma.org\/?p=42323"},"modified":"2023-05-06T16:39:33","modified_gmt":"2023-05-06T08:39:33","slug":"%e5%a4%a7%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b%e5%81%9a%e7%a7%91%e7%a0%94%e7%9a%84n%e7%a7%8d%e5%8f%af%e8%83%bd%e6%80%a7%ef%bc%9a%e4%bb%8e%e8%87%aa%e4%b8%bb%e8%bf%9b%e8%a1%8c%e7%a7%91%e5%ad%a6%e5%ae%9e","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=42323","title":{"rendered":"\u5927\u8bed\u8a00\u6a21\u578b\u505a\u79d1\u7814\u7684N\u79cd\u53ef\u80fd\u6027\uff1a\u4ece\u81ea\u4e3b\u8fdb\u884c\u79d1\u5b66\u5b9e\u9a8c\u5230\u5199\u7efc\u8ff0\u6587\u7ae0"},"content":{"rendered":"
\n
\n
\n
\n

<\/p>\n<\/section>\n

\n
\n
\n
\n
\n
\n

<\/section>\n<\/section>\n
\n
\n

\u5bfc\u8bed<\/strong><\/p>\n<\/section>\n<\/section>\n

\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
\n
\n

\u5927\u8bed\u8a00\u6a21\u578b\u7684\u901a\u7528\u6027\u5e26\u6765\u4e86\u5e7f\u6cdb\u7684\u5e94\u7528\u524d\u666f\u3002\u5927\u8bed\u8a00\u6a21\u578b\u53ef\u4ee5\u81ea\u4e3b\u8fdb\u884c\u79d1\u5b66\u5b9e\u9a8c\uff0c\u5408\u6210\u5316\u5408\u7269\uff0c\u9884\u6d4b\u65b0\u6750\u6599\u6027\u80fd\uff0c\u5199\u7efc\u8ff0\u6587\u7ae0\uff0c\u9884\u6d4b\u80a1\u7968\u4ef7\u683c…… \u672c\u6587\u7f57\u5217\u4e86\u5c06\u5927\u8bed\u8a00\u6a21\u578b\u5e94\u7528\u4e8e\u79d1\u5b66\u7814\u7a76\u7684\u79cd\u79cd\u5c1d\u8bd5\uff0c\u5305\u62ec\u751f\u7269\u533b\u836f\u3001\u5316\u5b66\u3001\u6750\u6599\u79d1\u5b66\u3001\u6c14\u5019\u79d1\u5b66\u3001\u5de5\u7a0b\u3001\u7ecf\u6d4e\u91d1\u878d\u3001\u79d1\u5b66\u5b66\u7b49\u5404\u4e2a\u9886\u57df\u3002<\/strong><\/p>\n


<\/section>\n<\/section>\n
\u5173\u952e\u8bcd\uff1a\u5927\u8bed\u8a00\u6a21\u578b\uff0c\u79d1\u5b66\u53d1\u73b0<\/span><\/strong><\/strong><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/strong><\/strong><\/span><\/strong><\/span><\/strong><\/strong><\/strong><\/section>\n
<\/strong><\/strong><\/strong><\/section>\n
<\/strong><\/strong><\/strong><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
<\/strong><\/section>\n<\/section>\n
\n

\u90ed\u745e\u4e1c<\/span> <\/span>| \u4f5c\u8005<\/strong><\/span><\/span><\/p>\n


<\/p>\n


<\/p>\n<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5927\u8bed\u8a00\u6a21\u578b x \u79d1\u7814<\/strong><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
 <\/span><\/section>\n
1. \u81ea\u4e3b\u8fdb\u884c\u79d1\u5b66\u5b9e\u9a8c<\/span><\/strong><\/span><\/section>\n

<\/span><\/strong><\/span><\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aEmergent autonomous scientific research capabilities of large language models<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.05332<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u8be5\u7814\u7a76\u6784\u5efa\u4e86\u540d\u4e3a agent \u7684\u7ed3\u5408\u591a\u79cd\u5927\u8bed\u8a00\u6a21\u578b\u7684\u667a\u80fd\u4e3b\u4f53\u7cfb\u7edf\uff0c\u53ef\u6839\u636e\u7528\u6237\u63d0\u793a\uff0c\u81ea\u4e3b\u8fdb\u884c\u79d1\u5b66\u5b9e\u9a8c\u7684\u8bbe\u8ba1\u3001\u8ba1\u5212\u548c\u6267\u884c\u3002\u8bba\u6587\u5c55\u793a agent \u4ece\u4e8b\u79d1\u5b66\u7814\u7a76\u80fd\u529b\u7684\u4e09\u4e2a\u4e0d\u540c\u4f8b\u5b50\uff0c\u5206\u522b\u4e3a\u641c\u7d22\u5236\u5b9a\u5408\u6210\u5e03\u6d1b\u82ac\u7684\u6d41\u7a0b\uff0c\u63a7\u5236\u591a\u4eea\u5668\u7cfb\u7edf\u8fdb\u884c\u8bd5\u7ba1\u79fb\u6db2\uff0c\u6210\u529f\u5730\u50ac\u5316\u4ea4\u53c9\u5076\u8054\u53cd\u5e94\u3002<\/span><\/section>\n
 <\/span><\/section>\n
\u4e0e AutoGPT \u7c7b\u4f3c\uff0cAgent \u7684\u6838\u5fc3\u662f\u4e00\u4e2a\u57fa\u4e8e\u5927\u8bed\u8a00\u6a21\u578b\u7684\u89c4\u5212\u5668\uff0c\u53ef\u6839\u636e\u7528\u6237\u8f93\u5165\u7684\u63d0\u793a\u5f00\u5c55\u884c\u52a8\uff0c\u53ef\u5f00\u5c55\u7684\u884c\u52a8\u5305\u62ec\u8bbf\u95ee\u4e92\u8054\u7f51\u641c\u7d22\u4fe1\u606f\uff0c\u901a\u8fc7 python \u6267\u884c\u8ba1\u7b97\uff0c\u83b7\u53d6\u6587\u6863\u4e2d\u7684\u4fe1\u606f\uff0c\u5e76\u5c55\u5f00\u5b9e\u9a8c\u3002\u5982\u56fe1\u6240\u793a\uff1a<\/span><\/section>\n

<\/section>\n
<\/section>\n
\u56fe1\uff1aAgent \u7684\u7cfb\u7edf\u6a21\u5757\uff0c\u5728\u591a\u4e2a\u6a21\u5757\u4e4b\u95f4\u4ea4\u6362\u4fe1\u606f\u3002<\/span><\/section>\n

<\/section>\n

<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5927\u8bed\u8a00\u6a21\u578b x \u751f\u7269\u533b\u5b66<\/strong><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
 <\/span><\/section>\n
2. \u751f\u6210\u751f\u7269\u5b9e\u9a8c\u7684\u64cd\u4f5c\u6307\u4ee4<\/span><\/strong><\/span><\/section>\n
 <\/span><\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aLLMs can generate robotic scripts from goal-oriented instructions in biological laboratory automation<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.10267<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/span><\/section>\n
\u7814\u7a76\u4eba\u5458\u4f7f\u7528\u5b9e\u9a8c\u5ba4\u81ea\u52a8\u5316\u53ef\u5927\u5927\u52a0\u5feb\u79d1\u5b66\u6d3b\u52a8\u3002\u7136\u800c\uff0c\u4f7f\u7528\u8ba1\u7b97\u673a\u7a0b\u5e8f\u64cd\u4f5c\u673a\u5668\u4eba\u4ee5\u5b9e\u73b0\u5b9e\u9a8c\u5ba4\u81ea\u52a8\u5316\uff0c\u9700\u8981\u6280\u672f\u77e5\u8bc6\u548c\u6280\u80fd\uff0c\u53ef\u80fd\u4e0d\u4f1a\u6210\u4e3a\u7814\u7a76\u4eba\u5458\u8bad\u7ec3\u6216\u4e13\u4e1a\u77e5\u8bc6\u7684\u4e00\u90e8\u5206\u3002\u5728\u8fc7\u53bb\u51e0\u5e74\u4e2d\uff0c\u5df2\u7ecf\u51fa\u73b0\u4e86\u4ee4\u4eba\u77a9\u76ee\u7684\u5927\u8bed\u8a00\u6a21\u578b\uff0c\u5982 GPT-4 \u53ef\u4ee5\u57fa\u4e8e\u81ea\u7136\u8bed\u8a00\u6307\u4ee4\u751f\u6210\u8ba1\u7b97\u673a\u4ee3\u7801\u3002<\/span><\/section>\n

<\/section>\n
\u8fd9\u9879\u7814\u7a76\u4f7f\u7528\u5927\u8bed\u8a00\u6a21\u578b\uff0c\u5305\u62ec GPT-4\uff0c\u5728\u57fa\u4e8e\u6a21\u7cca\u6307\u4ee4\u7684\u751f\u7269\u5b9e\u9a8c\u4e2d\u751f\u6210\u673a\u5668\u4eba\u64cd\u4f5c\u811a\u672c\u3002GPT-4 \u6210\u529f\u6839\u636e\u81ea\u7136\u8bed\u8a00\u7684\u7b80\u5355\u6307\u4ee4\u4e3a OT-2 \u751f\u6210\u811a\u672c\uff0cOT-2 \u662f\u4e00\u79cd\u4e0d\u6307\u5b9a\u673a\u5668\u4eba\u884c\u52a8\u7684\u57fa\u7840\u4e0a\uff0c\u81ea\u52a8\u5316\u8fdb\u884c\u6db2\u4f53\u5904\u7406\u7684\u673a\u5668\u4eba\u8bed\u8a00\u3002<\/span><\/section>\n

<\/section>\n
\u4f20\u7edf\u4e0a\uff0c\u5c06\u751f\u7269\u5b66\u7684\u7ec6\u5fae\u5dee\u522b\u7ffb\u8bd1\u4e3a\u5e95\u5c42\u7684\u673a\u5668\u4eba\u52a8\u4f5c\u6307\u4ee4\uff0c\u9700\u8981\u7814\u7a76\u4eba\u5458\u540c\u65f6\u4e86\u89e3\u751f\u7269\u5b66\u548c\u673a\u5668\u4eba\u5b66\uff0c\u60f3\u8c61\u673a\u5668\u52a8\u4f5c\uff0c\u5199\u673a\u5668\u811a\u672c\u3002\u8be5\u7814\u7a76\u663e\u793a GPT-4 \u53ef\u4ee5\u901a\u8fc7\u7b80\u5355\u7684\u63d0\u793a\uff0c\u7ed3\u5408\u4e13\u5bb6\u7ea7\u7684\u4e0a\u4e0b\u6587\u7406\u89e3\uff0c\u6307\u6325\u673a\u5668\u4eba\u64cd\u4f5c\u751f\u7269\u5b66\u5b9e\u9a8c\u3002\u5bf9\u4e8e\u751f\u7269\u5b66\u7814\u7a76\u4eba\u5458\uff0c\u8003\u8651\u673a\u5668\u64cd\u4f5c\u7ec6\u8282\u7f16\u5199\u6307\u4ee4\u662f\u4e00\u9879\u7e41\u7410\u7684\u4efb\u52a1\uff0c\u800c\u901a\u8fc7\u81ea\u7136\u8bed\u8a00\u7ed9\u51fa\u6307\u4ee4\uff0c\u4e0d\u5fc5\u8003\u8651\u673a\u5668\u4eba\u7684\u884c\u4e3a\uff0c\u5927\u5927\u589e\u52a0\u4e86\u80fd\u591f\u4ece\u81ea\u52a8\u5316\u751f\u7269\u5b9e\u9a8c\u4e2d\u53d7\u76ca\u7684\u7814\u7a76\u4eba\u5458\u7684\u6570\u91cf\u3002<\/span><\/section>\n

<\/section>\n
<\/section>\n
\u56fe2\uff1aGPT4\u751f\u6210\u64cd\u4f5c\u6307\u4ee4\u7684\u67b6\u6784<\/span><\/section>\n

<\/section>\n
3. \u63d0\u9ad8\u751f\u7269\u533b\u5b66\u76f8\u5173\u4fe1\u606f\u83b7\u53d6\u7684\u6548\u7387<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aGeneGPT: Teaching Large Language Models to Use NCBI Web APIs<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.09667<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
NCBI <\/span>\uff08\u7f8e\u56fd\u56fd\u5bb6\u751f\u7269\u6280\u672f\u4fe1\u606f\u4e2d\u5fc3\uff09<\/span>\u7ef4\u62a4\u7740\u4e16\u754c\u4e0a\u6700\u5927\u7684\u751f\u7269\u533b\u5b66\u6570\u636e\u5e93\uff0c\u5305\u62ec\u57fa\u56e0\u5e8f\u5217\u3001\u86cb\u767d\u8d28\u7ed3\u6784\u3001\u5316\u5408\u7269\u6027\u8d28\uff0c\u4ee5\u53ca\u751f\u7269\u533b\u5b66\u6587\u672c\uff0c\u5e76\u901a\u8fc7\u7edf\u4e00\u7684 Web API \u63d0\u4f9b\u6570\u636e\u63a5\u53e3\u3002\u901a\u8fc7\u8ba9GPT \u83b7\u53d6\u76f8\u5173 web \u63a5\u53e3\uff0c\u53ef\u4ee5\u63d0\u5347\u76f8\u5173\u7814\u7a76\u8005\u83b7\u53d6\u4fe1\u606f\u7684\u6548\u7387\uff0c\u8ba9\u666e\u901a\u4eba\u80fd\u591f\u901a\u8fc7\u81ea\u7136\u8bed\u8a00\u83b7\u53d6\u76f8\u5173\u7684\u751f\u7269\u5b66\u77e5\u8bc6\u3002\u76f8\u6bd4 New bing\uff0cChatGPT \u7b49\u901a\u7528\u5de5\u5177\uff0c\u51c6\u786e\u6027\u66f4\u9ad8\u3002\u8be5\u7814\u7a76\u4ee3\u8868\u4e86\u5927\u8bed\u8a00\u6a21\u578b\u7684\u4e00\u7c7b\u5e94\u7528\u8303\u5f0f\uff0c\u5373\u901a\u8fc7\u63a5\u5165\u5b66\u79d1\u6570\u636e\u5e93\u548c\u5de5\u5177\u63a5\u53e3\uff0c\u63d0\u5347\u5927\u6a21\u578b\u5728\u5177\u4f53\u5b66\u79d1\u7684\u80fd\u529b\u3002<\/span><\/section>\n

<\/section>\n
<\/section>\n

\u56fe3\uff1aGeneGPT \u95ee\u7b54\u793a\u4f8b\uff0c\u80fd\u591f\u56de\u7b54\u9886\u57df\u76f8\u5173\u7684\u95ee\u9898\uff0c\u4f8b\u5982\u57fa\u56e0\u53d8\u5f02\u4e0e\u90a3\u4e9b\u75be\u75c5\u6709\u5173<\/span><\/p>\n


<\/section>\n
4. \u4ece\u533b\u5b66\u6587\u672c\u4e2d\u9012\u5f52\u5730\u63d0\u53d6\u7ed3\u6784\u5316\u4fe1\u606f<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aStructured prompt interrogation and recursive extraction of semantics (SPIRES): A method for populating knowledge bases using zero-shot learning<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.02711<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u57fa\u4e8e\u5927\u8bed\u8a00\u6a21\u578b\u7684\u96f6\u5c1d\u8bd5\u5b66\u4e60\u80fd\u529b\uff0c\u8be5\u5de5\u5177<\/span>\uff08SPIRES\uff09<\/span>\u53ef\u4ee5\u4ece\u533b\u5b66\u76f8\u5173\u6587\u672c\u4e2d\uff0c\u901a\u8fc7\u9012\u5f52\u5730\u5411GPT3+\u6a21\u578b\u63d0\u51fa\u95ee\u9898\uff0c\u83b7\u53d6\u6587\u672c\u4e2d\u5305\u542b\u7684\u77e5\u8bc6\uff0c\u5e76\u5c06\u5176\u8f93\u51fa\u4ee5\u7ed3\u6784\u5316\u7684\u8868\u7684\u5f62\u5f0f\u3002SPIRES \u5728\u4e0d\u540c\u9886\u57df\u7684\u5e94\u7528\uff0c\u5305\u62ec\u98df\u7269\u914d\u65b9\u7684\u63d0\u53d6\u3001\u591a\u7269\u79cd\u7ec6\u80de\u4fe1\u53f7\u901a\u8def\uff0c\u75be\u75c5\u6cbb\u7597\uff0c\u591a\u6b65\u836f\u7269\u673a\u5236\u7b49\u3002\u76f8\u6bd4\u73b0\u6709\u7684\u5173\u7cfb\u62bd\u53d6<\/span>\uff08Relation Extraction, RE\uff09<\/span>\u65b9\u6cd5\uff0cSPIRES \u6613\u4e8e\u5b9a\u5236\uff0c\u66f4\u52a0\u7075\u6d3b\u3002\u6700\u91cd\u8981\u7684\u662f\uff0c\u5177\u6709\u5728\u6ca1\u6709\u4efb\u4f55\u8bad\u7ec3\u6570\u636e\u7684\u60c5\u51b5\u4e0b\u6267\u884c\u65b0\u4efb\u52a1\u7684\u80fd\u529b\u3002<\/span><\/section>\n

<\/section>\n
<\/section>\n

\u56fe4\uff1aSPIRES\u67b6\u6784\uff0c\u5176\u8f93\u5165\u662f\u6587\u672c\u4e0e\u9884\u671f\u7684\u7ed3\u6784\u5316\u6a21\u677f\uff0c\u901a\u8fc7OntoGPT\u4ea7\u751fprompt\u4e0eGPT3+\u4e92\u52a8\uff0c\u7ed3\u5408\u516c\u5f00\u6570\u636e\u5e93\u751f\u6210\uff0c\u4ea7\u751f\u8f93\u5165\u6587\u672c\u4e2d\u5305\u542b\u7684\u7ed3\u6784\u5316\u77e5\u8bc6<\/span><\/p>\n


<\/section>\n
5. \u751f\u6210\u836f\u7269\u7814\u53d1\u76f8\u5173\u7efc\u8ff0<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aThe Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2212.08104<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u4eba\u5de5\u667a\u80fd\u6709\u53ef\u80fd\u5f7b\u5e95\u6539\u53d8\u836f\u7269\u53d1\u73b0\u8fc7\u7a0b\uff0c\u63d0\u9ad8\u6548\u7387\u3001\u51c6\u786e\u6027\u548c\u901f\u5ea6\u3002\u7136\u800c\uff0c\u4eba\u5de5\u667a\u80fd\u7684\u6210\u529f\u5e94\u7528\u53d6\u51b3\u4e8e\u9ad8\u8d28\u91cf\u6570\u636e\u7684\u63d0\u4f9b\u3001\u4f26\u7406\u95ee\u9898\u7684\u89e3\u51b3\uff0c\u4ee5\u53ca\u5bf9\u57fa\u4e8e\u4eba\u5de5\u667a\u80fd\u65b9\u6cd5\u5c40\u9650\u6027\u7684\u8ba4\u8bc6\u3002\u672c\u6587\u7efc\u8ff0\u4e86\u4eba\u5de5\u667a\u80fd\u5728\u8fd9\u4e00\u9886\u57df\u7684\u4f18\u52bf\u3001\u6311\u6218\u548c\u4e0d\u8db3\uff0c\u5e76\u63d0\u51fa\u514b\u670d\u76ee\u524d\u969c\u788d\u7684\u53ef\u80fd\u7b56\u7565\u548c\u9014\u5f84\u3002\u6587\u7ae0\u8ba8\u8bba\u4e86\u4eba\u5de5\u667a\u80fd\u7684\u6570\u636e\u589e\u5f3a\u3001\u89e3\u91ca\u6027\u4eba\u5de5\u667a\u80fd\u7684\u5e94\u7528\u3001\u4eba\u5de5\u667a\u80fd\u4e0e\u4f20\u7edf\u5b9e\u9a8c\u65b9\u6cd5\u7ed3\u5408\uff0c\u4ee5\u53ca\u4eba\u5de5\u667a\u80fd\u5728\u836f\u7269\u7814\u7a76\u4e2d\u7684\u6f5c\u5728\u4f18\u52bf\u3002\u603b\u7684\u6765\u8bf4\uff0c\u8fd9\u7bc7\u7efc\u8ff0\u5f3a\u8c03\u4e86\u4eba\u5de5\u667a\u80fd\u5728\u836f\u7269\u53d1\u73b0\u4e2d\u7684\u6f5c\u529b\uff0c\u5e76\u63d0\u4f9b\u4e86\u5728\u8fd9\u4e00\u9886\u57df\u5b9e\u73b0\u5176\u6f5c\u529b\u7684\u6311\u6218\u548c\u673a\u9047\u7684\u6df1\u523b\u89c1\u89e3\u3002<\/span><\/section>\n

<\/section>\n
\u8be5\u6587\u6d4b\u8bd5\u4e86\u4f7f\u7528 ChatGPT \u64b0\u5199\u8bc4\u8bba\u6027\u7efc\u8ff0\u7684\u80fd\u529b\uff0c\u7814\u7a76\u8005\u5c06\u5411 ChatGPT \u63d0\u95ee\u751f\u6210\u7684\u6587\u672c\u4f5c\u4e3a\u8d77\u70b9\uff0c\u5728\u8fdb\u884c\u5f7b\u5e95\u7684\u4fe1\u606f\u771f\u5b9e\u6027\u5ba1\u67e5\uff0c\u5e76\u5bf9 ChatGPT \u7684\u6587\u672c\u751f\u6210\u80fd\u529b\u8fdb\u884c\u8bc4\u4f30\u4e4b\u540e\uff0c\u4eba\u7c7b\u4f5c\u8005\u5b9e\u9645\u4e0a\u91cd\u5199\u4e86\u624b\u7a3f\uff0c\u52aa\u529b\u5728\u539f\u59cb\u8f93\u51fa\u548c\u79d1\u5b66\u6807\u51c6\u4e4b\u95f4\u4fdd\u6301\u5e73\u8861\u3002\u6700\u540e\u4e00\u8282\u8ba8\u8bba\u4e86\u4f7f\u7528\u4eba\u5de5\u667a\u80fd\u5b9e\u73b0\u8bba\u6587\u7efc\u8ff0\u8fd9\u4e00\u76ee\u7684\u7684\u4f18\u70b9\u548c\u5c40\u9650\u6027\u3002<\/span><\/section>\n

<\/section>\n
6. \u6839\u636e\u89c6\u9891\u56de\u7b54\u624b\u672f\u76f8\u5173\u95ee\u9898<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aSurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.09974<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u8fd9\u9879\u7814\u7a76\u8bbe\u8ba1\u4e86\u4e00\u4e2a\u7aef\u5230\u7aef\u53ef\u8bad\u7ec3\u7684\u8bed\u8a00-\u89c6\u89c9 GPT<\/span>\uff08LV-GPT\uff09<\/span>\u6a21\u578b\uff0c\u6269\u5c55 GPT2 \u6a21\u578b\u4ee5\u5305\u62ec\u89c6\u89c9\u8f93\u5165\u3002LV-GPT \u5305\u542b\u4e00\u4e2a\u7279\u5f81\u63d0\u53d6\u5668<\/span>\uff08\u89c6\u89c9\u6807\u8bb0\u5668\uff09<\/span>\u548c\u89c6\u89c9\u6807\u8bb0\u5d4c\u5165<\/span>\uff08\u6807\u8bb0\u7c7b\u578b\u548c\u59ff\u6001\uff09<\/span>\u3002\u4e3a\u4e86\u4ea7\u751f\u8fde\u8d2f\u7684\u957f\u6bb5\u843d\uff0c\u4f5c\u8005\u6a21\u4eff\u4eba\u7c7b\u7406\u89e3\u95ee\u9898\u5e76\u4ece\u56fe\u4e2d\u83b7\u5f97\u7b54\u6848\u601d\u7ef4\u4e60\u60ef\uff0c\u4ed4\u7ec6\u6392\u5217\u5355\u8bcd\u7684\u987a\u5e8f\uff0c\u5373\u51fa\u73b0\u5728\u56fe\u7247\u4e4b\u524d\u7684\u90a3\u4e2a\u8bcd\u3002\u5728\u5b9a\u91cf\u8bc4\u4f30\u4e2d\uff0c\u4f5c\u8005\u8bc1\u660e LV-GPT \u6a21\u578b\u5728\u4e24\u4e2a\u516c\u5f00\u53ef\u7528\u7684\u624b\u672f VQA \u6570\u636e\u96c6\u4e0a\u4f18\u4e8e\u5176\u4ed6\u6700\u5148\u8fdb\u7684 VQA \u6a21\u578b<\/span>\uff08\u57fa\u4e8e\u5185\u7aa5\u955c\u89c6\u89c9\u6311\u6218\u673a\u5668\u4eba\u573a\u666f\u5206\u5272\u548c CholecTriplet\uff09<\/span>\u3002<\/span><\/section>\n

<\/section>\n
<\/section>\n
\u56fe6\uff1a\u7aef\u5bf9\u7aef LV-GPT \u56de\u7b54\u624b\u672f\u76f8\u5173\u95ee\u9898\u65f6\u7684\u7684\u6d41\u7a0b<\/span><\/section>\n

<\/section>\n

<\/span><\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5927\u8bed\u8a00\u6a21\u578b x \u5316\u5b66<\/strong><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
 <\/span><\/section>\n
7. \u5408\u6210\u5168\u65b0\u5316\u5408\u7269<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aChemCrow: Augmenting large-language models with chemistry tools<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.05376<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u5927\u8bed\u8a00\u6a21\u578b\u5728\u8de8\u9886\u57df\u7684\u4efb\u52a1\u4e2d\u8868\u73b0\u51fa\u4e86\u5f88\u5f3a\u7684\u6027\u80fd\uff0c\u4f46\u662f\u5374\u5f88\u96be\u89e3\u51b3\u4e0e\u5316\u5b66\u76f8\u5173\u7684\u95ee\u9898\u3002\u6b64\u5916\uff0c\u8fd9\u4e9b\u6a21\u578b\u7f3a\u4e4f\u5916\u90e8\u77e5\u8bc6\u6765\u6e90\uff0c\u9650\u5236\u4e86\u5b83\u4eec\u5728\u79d1\u5b66\u5e94\u7528\u4e2d\u7684\u6709\u7528\u6027\u3002\u5728\u9879\u7814\u7a76\u4ecb\u7ecd\u4e86 ChemCrow\uff0c\u4e00\u79cd\u57fa\u4e8e\u5927\u8bed\u8a00\u6a21\u578b\u7684\u5316\u5b66\u7814\u7a76\u5de5\u5177\uff0c\u7528\u4e8e\u5b8c\u6210\u6709\u673a\u5408\u6210\u3001\u836f\u7269\u53d1\u73b0\u548c\u6750\u6599\u8bbe\u8ba1\u4efb\u52a1\u3002<\/span><\/section>\n

<\/section>\n
\u901a\u8fc7\u6574\u540813\u4e2a\u4e13\u5bb6\u8bbe\u8ba1\u7684\u5de5\u5177\uff0cChemCrow \u589e\u5f3a\u4e86\u5927\u8bed\u8a00\u6a21\u578b\u5728\u5316\u5b66\u65b9\u9762\u7684\u6027\u80fd\uff0c\u5e76\u4e14\u6d8c\u73b0\u51fa\u4e86\u65b0\u7684\u80fd\u529b\u3002\u5bf9ChemCrow\u7684\u8bc4\u4f30\uff0c\u5305\u62ec\u5927\u8bed\u8a00\u6a21\u578b\u548c\u4e13\u5bb6\u8bc4\u4f30\uff0c\u8bc1\u660e ChemCrow \u5728\u81ea\u52a8\u5316\u4e00\u7cfb\u5217\u4e0d\u540c\u7684\u5316\u5b66\u4efb\u52a1\u65b9\u9762\u7684\u6709\u6548\u6027\u3002\u4ee4\u4eba\u60ca\u8bb6\u7684\u662f\uff0c\u4f5c\u8005\u53d1\u73b0GPT-4 \u4f5c\u4e3a\u8bc4\u4f30\u8005\uff0c\u4e0d\u80fd\u5c06\u660e\u663e\u9519\u8bef\u7684\u3001\u7531 GPT-4 \u7ed9\u51fa\u7684\u56de\u7b54\uff0c\u4e0e\u6b63\u786e\u7684 GPT-4 + ChemCrow \u56de\u7b54\u533a\u5206\u5f00\u3002\u6ee5\u7528 ChemCrow \u7b49\u5de5\u5177\u7684\u98ce\u9669\u5f88\u5927\uff0c\u7814\u7a76\u4e2d\u8ba8\u8bba\u4e86\u5b83\u4eec\u7684\u6f5c\u5728\u5371\u5bb3\u3002\u8d1f\u8d23\u4efb\u5730\u4f7f\u7528 ChemCrow \u4e0d\u4ec5\u5e2e\u52a9\u4e13\u5bb6\u5316\u5b66\u5bb6\uff0c\u964d\u4f4e\u975e\u4e13\u5bb6\u7684\u969c\u788d\uff0c\u800c\u4e14\u901a\u8fc7\u5f25\u5408\u5b9e\u9a8c\u548c\u8ba1\u7b97\u5316\u5b66\u4e4b\u95f4\u7684\u5dee\u8ddd\uff0c\u4fc3\u8fdb\u79d1\u5b66\u8fdb\u6b65\u3002<\/span><\/section>\n

<\/section>\n
<\/section>\n
\u56fe7\uff1aChemChow \u7684\u67b6\u6784\u4e0e\u8f93\u5165\u8f93\u51fa\u793a\u610f<\/span><\/section>\n

<\/section>\n

<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5927\u8bed\u8a00\u6a21\u578b x \u6750\u6599\u79d1\u5b66<\/strong><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
 <\/span><\/section>\n
8. \u9009\u62e9\u5e76\u9884\u6d4b\u6750\u6599\u6027\u80fd<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aLarge Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.02213<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u5bf9\u4e8e\u63a2\u7d22\u5c16\u7aef\u6750\u6599\uff0c\u6570\u636e\u7684\u591a\u5c11\u5177\u6709\u8d8a\u6765\u8d8a\u91cd\u8981\u7684\u610f\u4e49\u3002\u8fd9\u4e9b\u6570\u636e\u901a\u8fc7\u624b\u5de5\u6216\u81ea\u52a8\u5316\u65b9\u6cd5\u4ea7\u751f\u3002\u7136\u800c\uff0c\u6750\u6599\u79d1\u5b66\u9886\u57df\u5bf9\u4e8e\u5982\u4f55\u5229\u7528\u8fd9\u4e9b\u4e30\u5bcc\u7684\u6570\u636e\u5b58\u5728\u6311\u6218\uff0c\u7279\u522b\u662f\u5f53\u6750\u6599\u662f\u6839\u636e\u5668\u4ef6\u6027\u80fd\u800c\u4e0d\u662f\u5b83\u4eec\u7684\u7279\u6027\u6765\u8bc4\u4f30\u65f6\u3002<\/span><\/section>\n

<\/section>\n
\u8be5\u7814\u7a76\u63d0\u51fa\u4e86\u4e00\u79cd\u65b0\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\u4efb\u52a1\u2014\u2014\u7ed3\u6784\u5316\u4fe1\u606f\u63a8\u7406\u89e3\u51b3\u6750\u6599\u79d1\u5b66\u4e2d\u8bbe\u5907\u7ea7\u4fe1\u606f\u63d0\u53d6\u7684\u590d\u6742\u6027\u3002\u5728\u73b0\u6709\u7684\u9499\u949b\u77ff\u578b\u592a\u9633\u80fd\u7535\u6c60 FAIR<\/span> (\u53ef\u67e5\u627e\uff0c\u53ef\u8bbf\u95ee\uff0c\u4e92\u64cd\u4f5c\uff0c\u53ef\u91cd\u7528\uff09<\/span>\u6570\u636e\u96c6\uff0c\u7ed3\u6784\u5316\u4fe1\u606f\u63a8\u7406\u53d6\u5f97\u4e8691.8% \u7684F1\u5f97\u5206\u548c\u6269\u5c55\u6570\u636e\u96c6\uff0c\u5e76\u5c06\u751f\u6210\u7684\u6570\u636e\u7ecf\u8fc7\u683c\u5f0f\u5316\u548c\u89c4\u8303\u5316\u5904\u7406\uff0c\u4f7f\u5176\u80fd\u591f\u76f4\u63a5\u88ab\u7528\u4f5c\u5728\u968f\u540e\u7684\u6570\u636e\u5206\u6790\u7684\u8f93\u5165\u3002\u8fd9\u4e00\u7279\u70b9\u8d4b\u4e88\u6750\u6599\u79d1\u5b66\u5bb6\u901a\u8fc7\u9009\u62e9\u9ad8\u8d28\u91cf\u7684\u8bc4\u8bba\u6587\u7ae0\u4ee5\u5728\u5176\u6240\u5728\u9886\u57df\u7814\u53d1\u6a21\u578b\u7684\u80fd\u529b\u3002<\/span><\/section>\n

<\/section>\n
\u6b64\u5916\uff0c\u4f5c\u8005\u4f7f\u7528\u5927\u8bed\u8a00\u6a21\u578b\u8bbe\u8ba1\u9884\u6d4b\u592a\u9633\u80fd\u7535\u6c60\u7684\u7535\u6c14\u6027\u80fd\uff0c\u548c\u8bbe\u8ba1\u6750\u6599\u6216\u5668\u4ef6\u7684\u76ee\u6807\u53c2\u6570\u5b9e\u9a8c\u3002\u5927\u8bed\u8a00\u6a21\u578b\u65e0\u9700\u7ecf\u8fc7\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u65b9\u6cd5\u7684\u7279\u5f81\u9009\u62e9\uff0c\u5c31\u53ef\u8fbe\u5230\u76f8\u8fd1\u7684\u6027\u80fd\uff0c\u7a81\u51fa\u4e86<\/span>\u5927\u8bed\u8a00\u6a21\u578b\u83b7\u53d6\u79d1\u5b66\u77e5\u8bc6\u548c\u8bbe\u8ba1\u7c7b\u4f3c\u6750\u6599\u7684\u65b0\u6750\u6599\u7684\u6f5c\u529b\u3002<\/span><\/section>\n

<\/section>\n
<\/section>\n
\u56fe8\uff1a\u7ed3\u6784\u5316\u4fe1\u606f\u63a8\u7406\u5728\u591a\u4efb\u52a1\u5b66\u4e60\u4e2d\u8d1f\u8d23\u7406\u89e3\u4efb\u52a1\u5e76\u4ea7\u751f\u76f8\u5e94\u7684\u8f93\u51fa<\/span><\/section>\n

<\/section>\n

<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5927\u8bed\u8a00\u6a21\u578b x \u5de5\u7a0b<\/strong><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
 <\/span><\/section>\n
9. \u641c\u7d22\u571f\u529b\u5de5\u7a0b\u76f8\u5173\u4fe1\u606f<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aGeotechnical Parrot Tales (GPT): Harnessing Large Language Models in geotechnical engineering<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.02138<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u672c\u6587\u63a2\u8ba8 chatgPT \u53ca\u5176\u5728\u571f\u529b\u5de5\u7a0b<\/span>\uff08geotechnical\uff09<\/span>\u4e2d\u7684\u5e94\u7528\u3002\u8ba8\u8bba\u4e0e\u8fd9\u4e9b\u6a21\u578b\u76f8\u5173\u7684\u6311\u6218\u548c\u9677\u9631\uff0c\u5e76\u5f3a\u8c03\u5728\u5e94\u5bf9\u8fd9\u4e9b\u6311\u6218\u65b9\u9762\u8fdb\u884c\u5de5\u7a0b\u8bbe\u8ba1\uff0c\u4ee5\u786e\u4fdd\u53ef\u9760\u548c\u51c6\u786e\u7684\u7ed3\u679c\u65b9\u9762\u53ca\u65f6\u884c\u52a8\u7684\u91cd\u8981\u6027\u3002\u5177\u4f53\u7684\u5e94\u7528\u573a\u666f\u5305\u62ec\u6784\u5efa\u4e00\u4e2a\u4e0a\u4e0b\u6587\u76f8\u5173\u7684\u4e13\u4e1a\u641c\u7d22\u5f15\u64ce\uff0c\u751f\u6210\u590d\u6742\u7684\u571f\u529b\u5de5\u7a0b\u4efb\u52a1\u6d41\u7684\u6574\u5408\u754c\u9762\uff0c\u4ee5\u53ca\u57fa\u4e8e\u601d\u7ef4\u94fe\u7684\u63a8\u7406\u3002<\/span><\/section>\n

<\/section>\n
<\/section>\n
\u56fe9. \u57fa\u4e8e\u5411\u91cf\u6570\u636e\u5e93\u7684\u4e0a\u4e0b\u6587\u76f8\u5173\u4e13\u4e1a\u641c\u7d22\u7684\u6846\u67b6<\/span><\/section>\n

<\/section>\n

<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5927\u8bed\u8a00\u6a21\u578b x \u7ecf\u6d4e\u91d1\u878d<\/strong><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
 <\/span><\/section>\n
10. \u6839\u636e\u65b0\u95fb\u6807\u9898\u5206\u6790\u60c5\u7eea\uff0c\u9884\u6d4b\u80a1\u7968\u4ef7\u683c<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aCan ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.07619<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u4f5c\u8005\u7814\u7a76\u4e86 ChatGPT \u548c\u5176\u4ed6\u5927\u578b\u8bed\u8a00\u6a21\u578b\u5229\u7528\u65b0\u95fb\u6807\u9898\u8fdb\u884c\u60c5\u7eea\u5206\u6790\uff0c\u8fdb\u800c\u9884\u6d4b\u80a1\u5e02\u6536\u76ca\u65b9\u9762\u7684\u6f5c\u529b\u3002\u7814\u7a76\u7528  ChatGPT \u6307\u51fa\u4e00\u4e2a\u7ed9\u5b9a\u6807\u9898\u5bf9\u516c\u53f8\u7684\u80a1\u7968\u662f\u597d\u7684\u3001\u574f\u7684\u8fd8\u662f\u4e0d\u76f8\u5173\u7684\u65b0\u95fb\u3002\u7136\u540e\u8ba1\u7b97\u4e00\u4e2a\u6570\u503c\u5f97\u5206\uff0c\u5e76\u8bb0\u5f55\u8fd9\u4e9b\u201cChatGPT \u5f97\u5206\u201d\u548c\u968f\u540e\u7684\u6bcf\u65e5\u80a1\u5e02\u6536\u76ca\u4e4b\u95f4\u7684\u6b63\u76f8\u5173\u6027\u3002<\/span><\/section>\n

<\/section>\n
\u7814\u7a76\u53d1\u73b0 ChatGPT \u4f18\u4e8e\u4f20\u7edf\u7684\u60c5\u7eea\u5206\u6790\u65b9\u6cd5\uff0c\u7814\u7a76\u8fd8\u53d1\u73b0\u66f4\u7b80\u5355\u7684 GPT-1\u3001 GPT-2\u548c BERT \u7b49\u6a21\u578b\u4e0d\u80fd\u51c6\u786e\u9884\u6d4b\u6536\u76ca\u7387\uff0c\u8868\u660e\u6536\u76ca\u7387\u53ef\u9884\u6d4b\u6027\u662f\u5927\u6a21\u578b\u7684\u4e00\u79cd\u6d8c\u73b0\u80fd\u529b\u3002\u8fd9\u4e9b\u7814\u7a76\u7ed3\u679c\u8868\u660e\uff0c\u5728\u6295\u8d44\u51b3\u7b56\u8fc7\u7a0b\u4e2d\u5f15\u5165\u5927\u8bed\u8a00\u6a21\u578b\u53ef\u4ee5\u63d0\u4f9b\u66f4\u51c6\u786e\u7684\u9884\u6d4b\uff0c\u5e76\u63d0\u9ad8\u6295\u8d44\u8005\u5728\u5b9a\u91cf\u4ea4\u6613\u7b56\u7565\u4e2d\u7684\u8868\u73b0\u3002<\/span><\/section>\n

<\/section>\n
<\/section>\n

\u56fe10\uff1a\u57fa\u4e8e ChatGPT \u7684\u4efd\u8fdb\u884c\u6a21\u62df\u4ea4\u6613\u7684\u6536\u76ca\uff0c\u5176\u4e2d\u9ed1\u7ebf\u4ee3\u8868\u4f7f\u7528\u6240\u6709\u65b0\u95fb\u800c\u975e\u4e0e\u6295\u8d44\u516c\u53f8\u76f8\u5173\u65b0\u95fb\u7684\u57fa\u7ebf\u7ec4<\/span><\/p>\n


<\/section>\n
<\/span>
<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5927\u8bed\u8a00\u6a21\u578b x \u6c14\u5019\u79d1\u5b66<\/strong><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
 <\/span><\/section>\n
11. \u57fa\u4e8e\u6743\u5a01\u6587\u6863\u53ef\u9760\u56de\u7b54\u6c14\u5019\u53d8\u5316\u95ee\u9898<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1achatIPCC: Grounding Conversational AI in Climate Science<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.05510<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u5927\u8bed\u8a00\u6a21\u578b\u5728\u95ee\u7b54\u4efb\u52a1<\/span> (QA) <\/span>\u4e2d\u53d6\u5f97\u4e86\u663e\u8457\u7684\u8fdb\u5c55\u3002\u7136\u800c\uff0c\u4ecd\u7136\u9762\u4e34\u4e24\u5927\u6311\u6218: \u5e7b\u89c9\u548c\u8bad\u7ec3\u9636\u6bb5\u540e\u8fc7\u65f6\u7684\u4fe1\u606f\u3002\u8fd9\u4e9b\u6311\u6218\u5728\u6c14\u5019\u53d8\u5316\u7b49\u5173\u952e\u9886\u57df\u5904\u4e8e\u4e2d\u5fc3\u5730\u4f4d\uff0c\u56e0\u4e3a\u5728\u8fd9\u4e9b\u9886\u57df\uff0c\u5728\u6709\u9650\u7684\u65f6\u95f4\u5185\u4ece\u53ef\u9760\u6765\u6e90\u83b7\u5f97\u51c6\u786e\u548c\u6700\u65b0\u7684\u4fe1\u606f\u662f\u5fc5\u4e0d\u53ef\u5c11\u7684\uff0c\u4e5f\u975e\u5e38\u56f0\u96be\u3002\u4e3a\u4e86\u514b\u670d\u8fd9\u4e9b\u969c\u788d\uff0c\u4e00\u4e2a\u6f5c\u5728\u7684\u89e3\u51b3\u65b9\u6848\u662f\u4e3a\u5927\u8bed\u8a00\u6a21\u578b\u63d0\u4f9b\u5916\u90e8\u7684\u3001\u79d1\u5b66\u51c6\u786e\u7684\u548c\u53ef\u9760\u7684\u6765\u6e90<\/span>\uff08\u957f\u671f\u8bb0\u5fc6\uff09<\/span>\uff0c\u4ee5\u4e0d\u65ad\u66f4\u65b0\u5b83\u4eec\u7684\u77e5\u8bc6\uff0c\u5e76\u9632\u6b62\u4f20\u64ad\u4e0d\u51c6\u786e\u3001\u4e0d\u6b63\u786e\u6216\u8fc7\u65f6\u7684\u4fe1\u606f\u3002<\/span><\/section>\n

<\/section>\n
\u8fd9\u9879\u7814\u7a76\u901a\u8fc7\u6574\u5408\u653f\u5e9c\u95f4\u6c14\u5019\u53d8\u5316\u4e13\u95e8\u59d4\u5458\u4f1a\u7b2c\u516d\u6b21\u8bc4\u4f30\u62a5\u544a<\/span>\uff08IPCC AR6\uff09<\/span>\u4e2d\u7684\u4fe1\u606f\u6765\u52a0\u5f3a GPT-4\uff0c\u8fd9\u662f<\/span>\u8be5\u9886\u57df\u4e2d\u6700\u5168\u9762\u3001\u6700\u65b0\u548c\u53ef\u9760\u7684\u4fe1\u606f\u6765\u6e90\u3002\u7814\u7a76\u5c55\u793a\u4e86\u5bf9\u8bdd AI chatIPCC\uff0c\u53ef\u4ee5\u5728https:\/\/www.chatclimate.ai\u4e0a\u8bd5\u7528\uff0c\u5e76\u5c55\u793a\u4e86\u5b83\u5728\u4e09\u4e2a\u4e0d\u540c\u7684 QA \u573a\u666f\u4e2d\u51c6\u786e\u56de\u7b54\u5177\u6709\u6311\u6218\u6027\u95ee\u9898\u7684\u80fd\u529b\u3002\u8bc4\u4f30\u8868\u660e\uff0c\u6df7\u5408 chatIPCC \u63d0\u4f9b\u4e86\u66f4\u51c6\u786e\u7684\u7b54\u6848\uff0c\u7a81\u51fa\u4e86\u8be5\u89e3\u51b3\u65b9\u6848\u7684\u6709\u6548\u6027\u3002\u8fd9\u79cd\u65b9\u6cd5\u53ef\u4ee5\u5f88\u5bb9\u6613\u5730\u4e3a\u7279\u5b9a\u9886\u57df\u7684\u804a\u5929\u673a\u5668\u4eba\u5b9a\u5236\uff0c\u4f7f\u5176\u4ea4\u4ed8\u53ef\u9760\u548c\u51c6\u786e\u7684\u4fe1\u606f\u3002<\/span><\/section>\n

<\/span><\/section>\n
<\/section>\n
\u56fe11\uff1achatIPCC\u7684\u4fe1\u606f\u5904\u7406\u6d41<\/span><\/section>\n

<\/section>\n

<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5927\u8bed\u8a00\u6a21\u578b x \u79d1\u5b66\u5b66<\/strong><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n
 <\/span><\/section>\n
12. \u57fa\u4e8e GPT \u7684\u79d1\u5b66\u8ba1\u91cf\u5b66\u7814\u7a76<\/span><\/strong><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\u8bba\u6587\u6807\u9898\uff1aA GPT-Based Approach for Scientometric Analysis: Exploring the Landscape of Artificial Intelligence Research<\/span><\/section>\n
\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/arxiv.org\/abs\/2304.09487<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u8fd9\u9879\u7814\u7a76\u63d0\u51fa\u4e86\u4e00\u4e2a\u5168\u9762\u7684\u65b9\u6cd5\uff0c\u4ee5\u89e3\u51b3\u79d1\u5b66\u8ba1\u91cf\u5206\u6790\u5728\u4eba\u5de5\u667a\u80fd<\/span>\uff08AI\uff09<\/span>\u8fd9\u4e2a\u5feb\u901f\u53d1\u5c55\u9886\u57df\u7684\u6311\u6218\u3002\u901a\u8fc7\u5c06\u4e0e\u4eba\u5de5\u667a\u80fd\u76f8\u5173\u7684\u641c\u7d22\u8bcd\u4e0eGPT\u7684\u9ad8\u7ea7\u8bed\u8a00\u5904\u7406\u80fd\u529b\u76f8\u7ed3\u5408\uff0c\u8be5\u7814\u7a76\u5f00\u53d1\u4e86\u4e00\u79cd\u9ad8\u5ea6\u7cbe\u786e\u7684\u65b9\u6cd5\u6765\u8bc6\u522b\u548c\u5206\u6790 Web of Science<\/span> (WoS) <\/span>\u6570\u636e\u5e93\u4e2d\u4e0e\u4eba\u5de5\u667a\u80fd\u76f8\u5173\u7684\u6587\u7ae0\u3002\u591a\u6b65\u9aa4\u8fc7\u6ee4\u65b9\u6cd5\u5305\u62ec\u57fa\u4e8e WoS \u5f15\u6587\u4e3b\u9898\u3001\u7c7b\u522b\u3001\u5173\u952e\u8bcd\u7b5b\u9009\u548c GPT \u5206\u7c7b\u4ee5\u627e\u51fa\u76f8\u5173\u8bba\u6587\u3002<\/span><\/section>\n

<\/section>\n
\u7814\u7a76\u901a\u8fc7\u51c6\u786e\u7387\u53ec\u56de\u7387\u8bc4\u4f30\u4e86\u8be5\u65b9\u6cd5\u7684\u6709\u6548\u6027\uff0c\u53d1\u73b0\u8be5\u65b9\u6cd5\u5728\u6574\u4e2a WoS \u8bed\u6599\u5e93\u4e2d\u6355\u83b7\u4e86\u5927\u7ea694% \u7684\u4eba\u5de5\u667a\u80fd\u76f8\u5173\u6587\u7ae0\uff0c\u51c6\u786e\u7387\u8fbe\u5230 90% \u3002\u968f\u540e\u4f5c\u8005\u5206\u6790\u4e86\u51fa\u7248\u7269\u6570\u91cf\u7684\u8d8b\u52bf\uff0c\u63ed\u793a\u4e86\u4ece2013\uff5e2022\u5e74\u7684\u6301\u7eed\u589e\u957f\u6a21\u5f0f\u548c\u4e0d\u65ad\u589e\u957f\u7684\u8de8\u5b66\u79d1\u6c34\u5e73\u3002\u4f5c\u8005\u5bf9\u9876\u7ea7\u56fd\u5bb6\u548c\u673a\u6784\u8fdb\u884c\u4e86\u5f15\u6587\u5206\u6790\u7814\u7a76\uff0c\u5e76\u5229\u7528\u5173\u952e\u8bcd\u5206\u6790\u548c GPT \u786e\u5b9a\u4e86\u5171\u540c\u7684\u7814\u7a76\u4e3b\u9898\u3002\u8fd9\u9879\u7814\u7a76\u5c55\u793a\u4e86\u57fa\u4e8eGPT\u7684\u65b9\u6cd5\u53ef\u4fc3\u8fdb\u51c6\u786e\u7684\u79d1\u5b66\u8ba1\u91cf\u5206\u6790\uff0c\u63d0\u4f9b\u5173\u4e8e\u8de8\u5b66\u79d1\u6027\u8d28\u548c\u8be5\u9886\u57df\u5173\u952e\u53c2\u4e0e\u8005\u7684\u6d1e\u5bdf\u3002<\/span><\/section>\n

<\/section>\n
<\/section>\n
\u56fe12\uff1a\u8bba\u6587\u641c\u7d22\u7684\u76f8\u5173\u6d41\u7a0b<\/span><\/section>\n

<\/section>\n

<\/section>\n
\n
\n
\n
\n

\u201c\u540eChatGPT\u201d\u8bfb\u4e66\u4f1a<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

\n


<\/p>\n

2022\u5e7411\u670830\u65e5\uff0c\u4e00\u4e2a\u73b0\u8c61\u7ea7\u5e94\u7528\u7a0b\u5e8f\u8bde\u751f\u4e8e\u4e92\u8054\u7f51\uff0c\u8fd9\u5c31\u662fOpenAI\u5f00\u53d1\u7684ChatGPT\u3002\u4ece\u95ee\u7b54\u5230\u5199\u7a0b\u5e8f\uff0c\u4ece\u63d0\u53d6\u6458\u8981\u5230\u8bba\u6587\u5199\u4f5c\uff0cChatGPT\u5c55\u73b0\u51fa\u4e86\u591a\u6837\u5316\u7684\u901a\u7528\u667a\u80fd\u3002\u4e8e\u662f\uff0c\u5fae\u8f6f\u3001\u8c37\u6b4c\u3001\u767e\u5ea6\u3001\u963f\u91cc\u3001\u8baf\u98de\uff0c\u4e92\u8054\u7f51\u5927\u4f6c\u4eec\u7eb7\u7eb7\u6469\u62f3\u64e6\u638c\u51c6\u5907\u5165\u573a\u2026\u2026\u4f46\u662f\uff0c\u8bf7\u5148\u51b7\u9759\u4e00\u4e0b\u2026\u2026 \u73b0\u5728 all in \u5927\u8bed\u8a00\u6a21\u578b\u662f\u5426\u771f\u7684\u5408\u9002\uff1f\u8981\u77e5\u9053\uff0cChatGPT\u7684\u80cc\u540e\u5176\u5b9e\u5c31\u662f\u6df1\u5ea6\u5b66\u4e60+\u5927\u6570\u636e+\u5927\u6a21\u578b\uff0c\u800c\u8fd9\u4e9b\u8981\u7d20\u65e9\u57285\u5e74\u524d\u7684AlphaGo\u65f6\u671f\u5c31\u5df2\u7ecf\u5f00\u59cb\u706b\u70ed\u4e86\u30025\u5e74\u524d\u6ca1\u6709\u6293\u4f4f\u673a\u9047\uff0c\u73b0\u5728\u53c8\u51ed\u4ec0\u4e48\u53ef\u4ee5\u642d\u4e0a\u5927\u8bed\u8a00\u6a21\u578b\u8fd9\u8d9f\u5217\u8f66\u5462\uff1f<\/span><\/section>\n

<\/section>\n
\u96c6\u667a\u4ff1\u4e50\u90e8\u7279\u522b\u7ec4\u7ec7\u201c\u540e ChatGPT\u201d\u8bfb\u4e66\u4f1a<\/a>\uff0c\u7531\u5317\u5e08\u5927\u6559\u6388\u3001\u96c6\u667a\u4ff1\u4e50\u90e8\u521b\u59cb\u4eba\u5f20\u6c5f\u8001\u5e08\u8054\u5408\u8096\u8fbe\u3001\u674e\u5ae3\u7136\u3001\u5d14\u9e4f\u3001\u4faf\u6708\u6e90\u3001\u949f\u7ff0\u5ef7\u3001\u5362\u71da\u7b49\u591a\u4f4d\u8001\u5e08\u5171\u540c\u53d1\u8d77\uff0c\u65e8\u5728\u7cfb\u7edf\u6027\u5730\u68b3\u7406ChatGPT\u6280\u672f\uff0c\u5e76\u53d1\u73b0\u5176\u5f31\u70b9\u4e0e\u77ed\u677f\u3002\u672c\u7cfb\u5217\u8bfb\u4e66\u4f1a\u7ebf\u4e0a\u8fdb\u884c\uff0c2023\u5e743\u67083\u65e5\u5f00\u59cb\uff0c\u6bcf\u5468\u4e94\u665a\uff0c\u6b22\u8fce\u62a5\u540d\u4ea4\u6d41\u3002<\/span><\/section>\n


<\/p>\n<\/section>\n

<\/span><\/a>
<\/p>\n

\u8be6\u60c5\u8bf7\u89c1\uff1a
<\/span><\/section>\n
\u201c\u540e ChatGPT\u201d\u8bfb\u4e66\u4f1a\u542f\u52a8\uff1a\u4ece\u901a\u7528\u4eba\u5de5\u667a\u80fd\u5230\u610f\u8bc6\u673a\u5668<\/a>
<\/section>\n

<\/section>\n

<\/section>\n
\n
\n
\n
\n

AI+Science \u8bfb\u4e66\u4f1a<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n

\n


<\/p>\n<\/section>\n

AI+Science \u662f\u8fd1\u5e74\u5174\u8d77\u7684\u5c06\u4eba\u5de5\u667a\u80fd\u548c\u79d1\u5b66\u76f8\u7ed3\u5408\u7684\u4e00\u79cd\u8d8b\u52bf\u3002\u4e00\u65b9\u9762\u662f AI for Science\uff0c\u673a\u5668\u5b66\u4e60\u548c\u5176\u4ed6 AI \u6280\u672f\u53ef\u4ee5\u7528\u6765\u89e3\u51b3\u79d1\u5b66\u7814\u7a76\u4e2d\u7684\u95ee\u9898\uff0c\u4ece\u9884\u6d4b\u5929\u6c14\u548c\u86cb\u767d\u8d28\u7ed3\u6784\uff0c\u5230\u6a21\u62df\u661f\u7cfb\u78b0\u649e\u3001\u8bbe\u8ba1\u4f18\u5316\u6838\u805a\u53d8\u53cd\u5e94\u5806\uff0c\u751a\u81f3\u50cf\u79d1\u5b66\u5bb6\u4e00\u6837\u8fdb\u884c\u79d1\u5b66\u53d1\u73b0\uff0c\u88ab\u79f0\u4e3a\u79d1\u5b66\u53d1\u73b0\u7684\u201c\u7b2c\u4e94\u8303\u5f0f\u201d\u3002\u53e6\u4e00\u65b9\u9762\u662f Science for AI\uff0c\u79d1\u5b66\u5c24\u5176\u662f\u7269\u7406\u5b66\u4e2d\u7684\u89c4\u5f8b\u548c\u601d\u60f3\u542f\u53d1\u673a\u5668\u5b66\u4e60\u7406\u8bba\uff0c\u4e3a\u4eba\u5de5\u667a\u80fd\u7684\u53d1\u5c55\u63d0\u4f9b\u5168\u65b0\u7684\u89c6\u89d2\u548c\u65b9\u6cd5\u3002<\/span><\/section>\n

<\/section>\n
\u96c6\u667a\u4ff1\u4e50\u90e8\u8054\u5408\u65af\u5766\u798f\u5927\u5b66\u8ba1\u7b97\u673a\u79d1\u5b66\u7cfb\u535a\u58eb\u540e\u7814\u7a76\u5458\u5434\u6cf0\u9716\uff08Jure Leskovec \u6559\u6388\u6307\u5bfc\uff09\u3001\u54c8\u4f5b\u91cf\u5b50\u8ba1\u5212\u7814\u7a76\u5458\u6248\u9e3f\u4e1a\u3001\u9ebb\u7701\u7406\u5de5\u5b66\u9662\u7269\u7406\u7cfb\u535a\u58eb\u751f\u5218\u5b50\u9e23\uff08Max Tegmark \u6559\u6388\u6307\u5bfc\uff09\uff0c\u5171\u540c\u53d1\u8d77\u4ee5\u201cAI+Science<\/a>\u201d\u4e3a\u4e3b\u9898\u7684\u8bfb\u4e66\u4f1a\uff0c\u63a2\u8ba8\u8be5\u9886\u57df\u7684\u91cd\u8981\u95ee\u9898\uff0c\u5171\u5b66\u5171\u7814\u76f8\u5173\u6587\u732e\u3002\u8bfb\u4e66\u4f1a\u4ece2023\u5e743\u670826\u65e5\u5f00\u59cb\uff0c\u6bcf\u5468\u65e5\u65e9\u4e0a 9:00-11:00 \u7ebf\u4e0a\u4e3e\u884c\uff0c\u6301\u7eed\u65f6\u95f4\u9884\u8ba110\u5468\u3002\u6b22\u8fce\u5bf9\u63a2\u7d22\u8fd9\u4e2a\u6fc0\u52a8\u4eba\u5fc3\u7684\u524d\u6cbf\u9886\u57df\u6709\u5174\u8da3\u7684\u670b\u53cb\u62a5\u540d\u53c2\u4e0e\u3002<\/span><\/section>\n

<\/section>\n
<\/span><\/span><\/a><\/section>\n

<\/section>\n
\u8be6\u60c5\u8bf7\u89c1\uff1a<\/span><\/section>\n
\u4eba\u5de5\u667a\u80fd\u548c\u79d1\u5b66\u53d1\u73b0\u76f8\u4e92\u8d4b\u80fd\u7684\u65b0\u8303\u5f0f\uff1aAI+Science \u8bfb\u4e66\u4f1a\u542f\u52a8<\/a><\/section>\n

<\/span><\/section>\n

<\/span><\/section>\n
\n

\u63a8\u8350\u9605\u8bfb<\/span><\/strong><\/strong><\/p>\n

1. <\/strong>\u5723\u5854\u83f2\u5b66\u8005\uff1aAI \u5927\u8bed\u8a00\u6a21\u578b\u771f\u7684\u7406\u89e3\u4eba\u7c7b\u8bed\u8a00\u5417\uff1f<\/a><\/strong><\/span><\/strong><\/section>\n
2.<\/strong> \u201c\u610f\u8bc6\u673a\u5668\u201d\u521d\u63a2\uff1a\u5982\u4f55\u8ba9\u5927\u8bed\u8a00\u6a21\u578b\u5177\u5907\u81ea\u6211\u610f\u8bc6\uff1f<\/a><\/strong><\/span><\/strong><\/section>\n
3.<\/strong><\/strong> Science\u524d\u6cbf\uff1a\u5927\u8bed\u8a00\u6a21\u578b\u6d8c\u73b0\u6f14\u5316\u4fe1\u606f\uff0c\u52a0\u901f\u86cb\u767d\u8d28\u7ed3\u6784\u9884\u6d4b<\/a><\/strong><\/span><\/section>\n
4. \u300a\u5f20\u6c5f\u00b7\u590d\u6742\u79d1\u5b66\u524d\u6cbf27\u8bb2\u300b\u5b8c\u6574\u4e0a\u7ebf\uff01<\/strong><\/a><\/strong><\/strong><\/strong><\/section>\n
<\/strong><\/a><\/strong><\/strong><\/strong><\/section>\n
5. \u6210\u4e3a\u96c6\u667aVIP\uff0c\u89e3\u9501\u5168\u7ad9\u8bfe\u7a0b\uff0f\u8bfb\u4e66\u4f1a<\/span><\/strong><\/a><\/strong><\/strong><\/strong><\/strong><\/section>\n
6. <\/strong><\/strong><\/strong>\u52a0\u5165\u96c6\u667a\uff0c\u4e00\u8d77\u590d\u6742\uff01<\/strong><\/a><\/strong><\/strong><\/strong><\/span><\/section>\n


<\/strong><\/strong><\/strong><\/span><\/p>\n


<\/p>\n<\/section>\n

\u70b9\u51fb\u201c\u9605\u8bfb\u539f\u6587\u201d\uff0c\u62a5\u540d\u8bfb\u4e66\u4f1a<\/span><\/strong><\/section>\n

<\/mp-style-type><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

\u5bfc\u8bed \u5927\u8bed\u8a00\u6a21\u578b\u7684\u901a\u7528\u6027\u5e26\u6765\u4e86\u5e7f\u6cdb\u7684\u5e94\u7528\u524d\u666f\u3002\u5927\u8bed\u8a00\u6a21\u578b\u53ef\u4ee5\u81ea\u4e3b\u8fdb\u884c\u79d1\u5b66\u5b9e\u9a8c\uff0c\u5408\u6210\u5316\u5408\u7269\uff0c\u9884\u6d4b\u65b0\u6750\u6599\u6027\u80fd\uff0c\u5199\u7efc\u8ff0\u6587\u7ae0\uff0c\u9884\u6d4b\u80a1\u7968\u4ef7\u683c…… \u672c\u6587\u7f57\u5217\u4e86\u5c06\u5927\u8bed\u8a00\u6a21\u578b\u5e94\u7528\u4e8e\u79d1\u5b66\u7814\u7a76\u7684\u79cd\u79cd\u5c1d\u8bd5\uff0c\u5305\u62ec\u751f\u7269\u533b\u836f\u3001\u5316\u5b66\u3001\u6750\u6599\u79d1\u5b66\u3001\u6c14\u5019\u79d1\u5b66\u3001\u5de5\u7a0b\u3001\u7ecf\u6d4e\u91d1\u878d\u3001\u79d1\u5b66\u5b66\u7b49\u5404\u4e2a\u9886\u57df\u3002 \u5173\u952e\u8bcd\uff1a\u5927\u8bed\u8a00\u6a21…<\/p>\n","protected":false},"author":0,"featured_media":42310,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"special":[],"_links":{"self":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/42323"}],"collection":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=42323"}],"version-history":[{"count":0,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/42323\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/media\/42310"}],"wp:attachment":[{"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=42323"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=42323"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=42323"},{"taxonomy":"special","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fspecial&post=42323"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}