A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Floriane C. M. Braun
A nuisance-controlled residual-stream probing method for detecting benchmark contamination in language models.
Unknown
This paper investigates in-context learning in transformers and LLMs by training them to learn discrete Boolean functions, probing the role of attention and the underlying mechanisms.
Unknown
This paper investigates whether large reasoning models plan reasoning strength (number of reasoning tokens) before generating answers using linear probing.