StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions
Large language models often answer the same multiple-choice question inconsistently when it is posed under support-oriented and elimination-oriented framings. We investigate whether these discrepancies arise from different internal representations induced by the two framings. We introduce a dual-framing protocol with minimally varied prompts that use either support- or elimination-oriented framing while keeping the evaluation target fixed. To probe the internal computation, we append an untrained special token, [STATE], and treat its residual-stream activation as an intervention interface. Acr
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.
- FuzzyOverlapping authors or contributors · 62%mudler/LocalAI →
“Shared author/contributor keys: guo”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- LinkedLinked via arxiv author · 85%Chao Gao →
“StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions”
- LinkedLinked via arxiv author · 85%Haijiang Liu →
“StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions”
- LinkedLinked via arxiv author · 85%Qiyuan Liu →
“StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions”
- LinkedLinked via arxiv author · 85%Caicai Guo →
“StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions”
- LinkedLinked via arxiv author · 85%Frank van Harmelen →
“StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions”
- LinkedLinked via arxiv author · 85%Jinguang Gu →
“StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions”