Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning
Paper • 2606.25524 • Published • 2
Yukyung Lee
yukyung
AI & ML interests
NLP ♥︎ Eval
Recent Activity
authored a paper 12 days ago
LLMs Learn Better In-Context from Rules than from Examples authored a paper 12 days ago
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation authored a paper 12 days ago
AI Writers Have a Consistent Stylometric Footprint, but AI Editors Do NotOrganizations
![[HYU_NLP] EVA Team's profile picture](https://cdn-avatars.huggingface.co/v1/production/uploads/656dfa7227cb1927ca73384c/5K6l9OflbqHPStZ9zsvg-.jpeg)
upvoted a paper 3 months ago