164 citations · 164 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Localizing RL-Induced Tool Use to a Single Crosscoder Feature
Andrii Shportko, Shubham Bhokare, Ahmed Zeyad A Alzahrani +3
Fine-tuning through RL reshapes the internal representations of language models to enable agentic behaviors such as tool use, yet the mechanistic basis of these changes remains poo…
cs.CL2026
When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints
Yuheng Chen, Zhiyu Wu, Bowen Cheng +2
We identify and systematically characterize a class of task-structural alignment failures in large language models (LLMs): even when the harmful intent remains unchanged, changing…