Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs
Although LLMs have made significant progress in mathematical reasoning, determining whether a mathematical problem is solvable remains a fundamental yet challenging capability. While recent studies have probed internal representations of model solvability beliefs, verbalization has primarily been studied behaviorally rather than as an internal representation, limiting its analysis and manipulation. We address this gap by separately probing representations of solvability knowledge and verbalization, allowing us to disentangle the two within model hidden states. Across multiple LLMs, we show tha
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 47%benjaminzwhite/reasoning-models →
- PossiblePossibly related (embedding) · 46%sileod/llm-theory-of-mind →
- PossiblePossibly related (embedding) · 45%Retrace-1.5B →
- LinkedLinked via arxiv author · 85%Nikolaos Xiros →
“Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs”
- LinkedLinked via arxiv author · 85%Maria-Eleni Zoumpoulidi →
“Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs”
- LinkedLinked via arxiv author · 85%Georgios Paraskevopoulos →
“Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs”