热点
"事实性" 相关文章
Consistency Training Helps Stop Sycophancy and Jailbreaks
cs.AI updates on arXiv.org 2025-11-03T05:19:05.000000Z
Leveraging Hierarchical Organization for Medical Multi-document Summarization
cs.AI updates on arXiv.org 2025-10-28T04:14:35.000000Z
ACL 2025 | 北大提出动态焦点解码：让开放生成既“靠谱”又“好看”
PaperWeekly 2025-10-17T14:33:45.000000Z
ACL 2025 | 北大提出动态焦点解码：让开放生成既“靠谱”又“好看”
PaperWeekly 2025-10-17T14:33:45.000000Z
ACL 2025 | 北大提出动态焦点解码：让开放生成既“靠谱”又“好看”
PaperWeekly 2025-10-17T14:33:45.000000Z
ACL 2025 | 北大提出动态焦点解码：让开放生成既“靠谱”又“好看”
PaperWeekly 2025-10-16T14:38:10.000000Z
ACL 2025 | 北大提出动态焦点解码：让开放生成既“靠谱”又“好看”
PaperWeekly 2025-10-16T14:38:10.000000Z
Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
cs.AI updates on arXiv.org 2025-10-03T04:17:58.000000Z
Extrinsic Hallucinations in LLMs
Lil'Log 2025-09-25T10:02:04.000000Z
Benchmarking and Improving LLM Robustness for Personalized Generation
cs.AI updates on arXiv.org 2025-09-25T05:36:44.000000Z
文心新出的推理大模型，给了我们信心
机器之心 2025-09-11T16:05:31.000000Z
文心新出的推理大模型，给了我们信心
机器之心 2025-09-11T04:10:33.000000Z
ACL 2025 | 知道≠会说！UAlign用不确定性纠偏大模型幻觉，事实性对齐更进一步
PaperWeekly 2025-07-14T00:19:00.000000Z
ACL 2025 | 知道≠会说！UAlign用不确定性纠偏大模型幻觉，事实性对齐更进一步
PaperWeekly 2025-07-09T15:32:47.000000Z
LLM幻觉，竟因知识“以大欺小”，华人团队祭出对数线性定律与CoDA策略
36氪 - 科技频道 2025-04-07T09:53:46.000000Z
Alibaba发布：可编辑CoT，超越ReAct20%
PaperAgent 2024-12-17T09:27:40.000000Z
Extrinsic Hallucinations in LLMs
Lil'Log 2024-11-09T05:43:41.000000Z
OpenAI Lilian Weng万字长文解读LLM幻觉：从理解到克服
智源社区 2024-07-16T05:21:29.000000Z
OLAPH: A Simple and Novel AI Framework that Enables the Improvement of Factuality through Automatic Evaluations
MarkTechPost@AI 2024-05-27T14:30:55.000000Z