Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions
Paper • 2608.29109 • Published • 15
Donna Morgan
carloswashington
AI & ML interests
None yet
Recent Activity
upvoted a paper about 11 hours ago
Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions upvoted a paper about 14 hours ago
Procedural Graphs: Self-Evolving Execution Structures for LLM AgentsOrganizations
None yet