When Every Choice Is Correct: A Causal Study of Numerical Preference in Language Models
When a language model chooses a number between 1 and 30, every integer in the range is valid, yet the model can favor particular answers. We use numerical choice to study how preference is processed across layers and tokens.
By Hongnian Huang, Hongliang LiuarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Nov 5, 2026.
Comments
Sign in to join the discussion.