Author

Yan-Shan Lin

h-index 2 View on Semantic Scholar

We have 1 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence May 2026

Useful Memories Become Faulty When Continuously Updated by LLMs

This work traces the regression to the consolidation step rather than the underlying experience: the same trajectories yield qualitatively different memories under different update schedules, and an episodic-only control that simply retains those trajectories remains competitive with the consolidators the authors test.

Dylan Zhang, Yan-Shan Lin, Zheng Wu et al. · arXiv.org · 10 citations