作者位次 #5/5ICLR 2026Poster· Applications / Language, Speech and Dialog
Do LLMs Forget What They Should? Evaluating In-Context Forgetting in Large Language Models
Yuli Qian · Zechuan Yang · Wenbiao Ding · Hongzhi Li · Yutao Xie
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Yuli Qian · Zechuan Yang · Wenbiao Ding · Hongzhi Li · Yutao Xie
Jie Deng · Hanshuang Tong · Jun Li · Shining Liang · Ning Wu · Hongzhi Li · Yutao Xie
Large language models (LLMs) have made impressive strides in mathematical reasoning, often fine-tuned using rejection sampling, which retains only correct reasoning trajectories. While effective, this paradigm treats supervision as a binary filter that systematically excludes teacher-generated er...
Junjie Li · Xinrui Guo · Yuhao Wu · Roy Ka-Wei Lee · Hongzhi Li · Yutao Xie
What happens when a storyteller forgets its own story? Large Language Models (LLMs) can now generate narratives spanning tens of thousands of words, but they often fail to maintain consistency throughout. When generating long-form narratives, these models can contradict their own established fact...