Eduard Tulchinskii

Topology of Attention Detects Hallucinations in Code LLMs

Edge-wise topological divergence gaps: guiding search in combinatorial optimization

Listening to the Wise Few: Query–Key Alignment Unlocks Latent Correct Answers in Large Language Models

Think First, Then Select and Verify with Query–Key Alignment

Listening to the Wise Few: Select-and-Copy Attention Heads for Multiple-Choice QA