AI RESEARCH
Consistency-Guided Decoding with Proof-Driven Disambiguation for Three-Way Logical Question Answering
arXiv CS.CL
•
ArXi:2604.06196v1 Announce Type: new Three-way logical question answering (QA) assigns $True/False/Unknown$ to a hypothesis $H$ given a premise set $S$. While modern large language models (LLMs) can be accurate on isolated examples, we identify two recurring failure modes in 3-way logic QA: (i) negation inconsistency, where answers to $H$ and $\neg H$ violate the deterministic label mapping, and (ii) epistemic $Unknown$, where the model predicts $Unknown$ due to uncertainty or instability even when $S$ entails one side.