神经符号结合方法让 LLM 精确求解 Zebra 逻辑谜题
From Natural Language to Exact Cover: A Neuro-Symbolic Approach to Zebra Puzzles
把逻辑谜题交给 LLM 解析、再丢给精确覆盖求解器算答案，纯 CoT 解不好的题这条路能稳定做对，做求解器集成可以参考。
arXiv 论文提出一种神经符号框架，让 LLM 将自然语言的 Zebra 逻辑谜题翻译成结构化工具调用，构建精确覆盖（exact cover）实例。随后由符号求解器计算答案，并利用 Zebra 谜题解的唯一性反馈迭代修正欠约束或过约束的编码。论文在多参数规模、多后训练范式和多个 LLM 家族上做了评测。结果显示该混合方法持续优于 CoT 提示等纯神经基线和近期神经符号方法。
From Natural Language to Exact Cover: A Neuro-Symbolic Approach to Zebra Puzzles
Chain-of-Thought (CoT) generation has substantially improved the performance of Large Language Models (LLMs) on complex reasoning tasks, including code generation, data analysis, and exam-style question answering. Despite these advances, purely neural LLMs continue to struggle with elementary logical reasoning problems and lack the determinism, soundness, and reliability characteristic of symbolic reasoning systems. Conversely, classical symbolic methods such as SAT solving and exact cover guarantee correctness and completeness, but require problems to be expressed in highly specialized formal encodings, limiting their applicability to natural language inputs. In this work, we present a synergistic neuro-symbolic framework that bridges this gap by combining neural semantic parsing with deterministic exact cover reasoning. Given a Zebra-style logic puzzle in natural language, an LLM translates entities and constraints into structured tool calls that construct an exact cover instance. A symbolic solver then computes the solution and provides feedback to iteratively refine invalid, under- or overconstrained encodings, exploiting the uniqueness property of Zebra puzzles. We conduct a comprehensive empirical evaluation across multiple parameter scales, post-training paradigms, and LLM families. The results demonstrate that our hybrid approach consistently outperforms strong plain neural baselines, including CoT prompting, as well as recent neuro-symbolic methods.
