通过迭代符号精修增强大语言模型的伦理解释
Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement
AI总结：
针对大语言模型伦理解释存在事实错误、逻辑一致性弱的问题，提出融合LLMs与反向链求解器的Logic-Explainer溯因-演绎框架，可精修解释、生成形式化证明，有效提升伦理NLI任务中解释质量与模型对齐性。
摘要：
自然语言推理（NLI）领域越来越多的研究聚焦于大语言模型（LLMs）的应用、评估及其推理能力。然而，尽管LLMs取得了成功，它们仍容易在解释中出现事实错误和不一致性，在复杂领域的推理中可控性和可解释性有限。本文聚焦伦理NLI，研究神经符号混合技术如何提升LLMs生成的伦理解释的逻辑有效性与对齐性。具体而言，我们提出了一个名为Logic-Explainer的溯因-演绎框架，该框架将LLMs与外部反向链求解器结合，对分步自然语言解释进行精修，同时验证其正确性、减少不完整性并最小化冗余。大量实证分析表明，在具有挑战性的伦理NLI任务上，Logic-Explainer能够改进通过上下文学习方法和思维链（CoT）生成的解释，同时生成描述并支撑模型推理的形式化证明。由于伦理NLI需要常识推理来识别潜在的道德违规行为，我们的结果更广泛地证明了神经符号方法在多步NLI任务中的有效性，为提升LLMs的逻辑一致性、可靠性和对齐性开辟了新方向。
英文摘要：
An increasing amount of research in Natural Language Inference (NLI) focuses on the application and evaluation of Large Language Models (LLMs) and their reasoning capabilities. Despite their success, however, LLMs are still prone to factual errors and inconsistencies in their explanations, offering limited control and interpretability for inference in complex domains. In this paper, we focus on ethical NLI, investigating how hybrid neuro-symbolic techniques can enhance the logical validity and alignment of ethical explanations produced by LLMs. Specifically, we present an abductive-deductive framework named Logic-Explainer, which integrates LLMs with an external backward-chaining solver to refine step-wise natural language explanations and jointly verify their correctness, reduce incompleteness and minimise redundancy. An extensive empirical analysis demonstrates that Logic-Explainer can improve explanations generated via in-context learning methods and Chain-of-Thought (CoT) on challenging ethical NLI tasks, while, at the same time, producing formal proofs describing and supporting models' reasoning. As ethical NLI requires commonsense reasoning to identify underlying moral violations, our results suggest the effectiveness of neuro-symbolic methods for multi-step NLI more broadly, opening new opportunities to enhance the logical consistency, reliability, and alignment of LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
