← 研踪 PaperTrailarXiv:2608.12836 · v2
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
首次提交 2026-08-13 13:18
版本更新 2026-10-26 14:24
雷达观测 2026-10-29 00:36
摘要
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.
作者备注：24 pages, 6 figures, 15 tables
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v2 · 2026-10-26 14:24 · 最新观测版本
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
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.
查看此版本解读 →查看此版本原文 ↗