[Submitted on 13 Aug 2026 (v1), last revised 26 Oct 2026 (this version, v2)]
Abstract:Large language models often fail when answer options require combining atomic judgments under explicit logical operators, even when they judge the individual atoms correctly. We study compound options connected by AND, OR, and NEITHER/NOR, introducing a framework that decomposes each option into atomic answers and scores contrastive hypotheses about each one, so the model never sees a compound option. An operator-constrained integer linear program then composes the calibrated scores into a single prediction. We evaluate on LOGICAL-COMMONSENSEQA and introduce LOGICAL-SATA, a reading-comprehension benchmark derived from SATA-Bench. Our framework improves Macro-F1 from 48.3 to 77.0 on the human-validated LOGICAL-COMMONSENSEQA split and from 47.6 to 75.6 on LOGICAL-SATA, with the largest gains on NEITHER/NOR.
Submission history
From: Obed Junias [view email]
[v1] Thu, 13 Aug 2026 05:18:55 UTC (4,235 KB)
[v2] Mon, 26 Oct 2026 06:24:16 UTC (4,246 KB)
