用小模型+符号推理，让大模型更准地做逻辑判断。
UFAL-CUNI at SemEval-2026 Task 11: An Efficient Modular Neuro-symbolic Method for Syllogistic Reasoning
- 用小语言模型解析自然语言为一阶逻辑，再交由符号证明器处理。
- 在多数子任务上准确率高，且内容干扰小，表现优于同类零样本模型。
- 适合研究逻辑推理与大模型偏见的学者，尤其关注可解释性者。
本文介绍我们提交至SemEval-2026 Task 11：解耦大语言模型中的内容与形式推理的系统。提出一种高效的模块化神经符号方法，结合符号证明器与小型推理型语言模型（40亿参数）。系统包含基于LLM的解析器，将自然语言三段论转换为一阶逻辑（FOL）表示，搭配自动定理证明器，并有两个可选模块：用于多语言输入的机器翻译，以及用于识别相关前提的符号检索组件。系统在多数子任务上达到有竞争力的准确率，且内容干扰较小。消融实验表明，该方法在该参数规模下优于基于LLM的零样本基线，但小型LLM的多语言能力有限。最后，我们讨论了任务主要评估指标并分析其局限性。
原文摘要 · Abstract (English)
This paper describes our system submitted to SemEval-2026 Task 11: Disentangling Content and Formal Reasoning in Large Language Models. We present an efficient modular neuro-symbolic approach, combining a symbolic prover with small reasoning LLMs (4B parameters). The system consists of an LLM-based parser that translates natural language syllogisms to a first-order logic (FOL) representation, an automated theorem prover, and two optional modules: machine translation for multilingual inputs and a symbolic retrieval component for the identification of relevant premises. The system achieves competitive accuracy and relatively low content effect on most subtasks. Our ablations show that this approach outperforms LLM-based zero-shot baselines in this parameter size range, but also reveal limited multilingual capabilities of small LLMs. Finally, we include a discussion of the task's main ranking metric and analyze its limitations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。