The Second Half：一位 OpenAI 科学家的 AI 下半场启示录
"评估方法" 相关文章
警惕AI“罕见”危险行为
让 LLM 来评判 | 奖励模型相关内容
直播｜LLM-as-a-Judge热门论文，当AI变成“判官”综述分享，AI+金融圆桌交流，IDEA研究院
Assessment in Computer Science Education in the GenAI Era
From Contradictions to Coherence: Logical Alignment in AI Models
DeepMind Research Introduces The FACTS Grounding Leaderboard: Benchmarking LLMs’ Ability to Ground Responses to Long-Form Input
你的专属“钢铁侠”助手OS Agents来了！浙大联手OPPO、零一万物等10个机构推出全新综述
This AI Paper Introduces LLM-as-an-Interviewer: A Dynamic AI Framework for Comprehensive and Adaptive LLM Evaluation
New Evals for Better Models, AI Research Papers Made Easier to Understand, Train Your Own Flux LoRA, and More
Red Teaming for AI: Strengthening Safety and Trust through External Evaluation
Researchers at Peking University Introduce A New AI Benchmark for Evaluating Numerical Understanding and Processing in Large Language Models
大模型也冲“奥斯卡”：港科大腾讯等提出AI角色扮演全景综述，四方面剖析关键细节
Sabotage Evaluations for Frontier Models
OpenAI 最新 53 页论文：ChatGPT 看人下菜碟，对“小美”和“小帅”回答不一致
Exposing Vulnerabilities in Automatic LLM Benchmarks: The Need for Stronger Anti-Cheating Mechanisms
Nature：连诺奖都拿了的AI，能像人类一样拥有常识吗？
连诺奖都拿了的AI，能像人类一样拥有常识吗？
一篇大模型NL2SQL框架全栈技术综述
6连板双成药业披露重大资产重组进展：标的公司奥拉股份估值将明显低于前次融资估值100亿元
