Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
arXiv:2603.03308v1 Announce Type: cross Abstract: How does the conversational past of large language models (LLMs) influence their future performance? Recent work suggests that LLMs are …
Adi Simhi, Fazl Barez, Martin Tutek, Yonatan Belinkov, Shay B. Cohen
10 views