Misaligning Reasoning with Answers -- A Framework for Assessing LLM CoT Robustness
Paper • 2505.17406 • Published
Calvin Xu
cmxu
AI & ML interests
Trustworthy ML
Recent Activity
upvoted a paper 11 days ago
TRACE: Capability-Targeted Agentic Training upvoted a paper 16 days ago
SEVerA: Verified Synthesis of Self-Evolving Agents authored a paper 16 days ago
Misaligning Reasoning with Answers -- A Framework for Assessing LLM CoT RobustnessOrganizations
None yet
authored 2
papers 16 days ago