从原子证据到逻辑组合：面向复合答案选项的结构化组合推理
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
AI 导读
该研究针对大语言模型在答案选项需要用 AND、OR、NEITHER/NOR 等逻辑算子组合原子判断时常出错的问题，提出将选项分解为原子答案、对每个原子做对比假设评分的框架，再用算子约束的整数线性规划组合出最终预测。
正文 · 原文
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.
| Comments: | 24 pages, 6 figures, 15 tables |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.12836 [cs.CL] |
| (or arXiv:2608.12836v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2608.12836 arXiv-issued DOI via DataCite |
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)
来源：arXiv cs.AI · arxiv.org