Hugging Face Trending Papers

Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One

Read the original on Hugging Face Trending Papers →

A language model's memory can be worse than having no memory at all. Give a model a memory that kept a wrong conclusion but dropped the work behind it, and it emits that stale value as a confident answer; give the same model an empty memory and it abstains.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Aug 12

From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents

arXiv:2608. 10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter reasoning, tool use, answers, and subsequent memory writes.

By Caili Yu, Yiqi Wang, Jiaqi Zhang, Yiqun Duan, Mingkai Zheng, Zhangkai Wu, Kaize Shi, Taotao Cai
arXiv AI
5d ago

Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues

arXiv:2608. 12599v1 Announce Type: new Abstract: Multi-turn dialogues let users revoke constraints as easily as impose them, but revocation does not reliably take effect: models keep enacting withdrawn requirements (occasionally beneath comments asserting their removal), a failure we call \emph{behavioral relapse}, or revocation inertia.

By Haoyuan Zhu