发表机构
University of Science and Technology of China（中国科学技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DARE提出多智能体辩证推理框架，通过关系约束检索、双向验证和置信度反思，在结构化知识事实核查中使8B模型达到88.12%准确率，媲美GPT-4o基线。
AI 中文摘要
结构化知识事实核查旨在通过推理结构化证据来确定自然语言主张的真实性。近期基于程序生成的方法利用大型语言模型（LLMs）生成可执行的图推理程序，在结构化知识事实核查基准上取得了强劲性能。然而，这些方法仍受限于无效关系生成、缺乏自我纠正的单路径推理，以及倾向于高估支持信号的偏见性证据评估。我们提出辩证智能体推理（DARE），一种多智能体框架，将结构化知识事实核查表述为迭代的检索-推理-反思过程。DARE整合了基于关系约束的证据检索以将推理限制在有效结构内，辩证双向验证以从支持和反驳两个视角评估证据，以及置信度驱动的元反思以动态确定是否需要额外的证据探索。大量实验证明了DARE在结构化知识事实核查中的有效性，其中8B骨干模型达到了88.12%的准确率，并匹配或超越了基于GPT-4o的程序生成基线，这证实了辩证智能体推理在激发LLMs潜在推理能力方面的功效。
英文摘要
Structured knowledge fact checking aims to determine the truthfulness of natural language claims by reasoning over structured evidence. Recent program-generation approaches leverage large language models (LLMs) to generate executable graph reasoning programs, achieving strong performance on structured knowledge fact checking benchmarks. However, these methods remain limited by invalid relation generation, single-path reasoning that lacks self-correction, and biased evidence assessment that tends to overestimate supporting signals. We propose Dialectical Agentic Reasoning (DARE), a multi-agent framework that formulates structured knowledge fact checking as an iterative retrieve-reason-reflect process. DARE integrates relation-grounded evidence retrieval to constrain reasoning to valid structures, dialectical bidirectional verification to evaluate evidence from both supporting and refuting perspectives, and confidence-driven meta-reflection to dynamically determine whether additional evidence exploration is necessary. Extensive experiments demonstrate the effectiveness of DARE in structured knowledge fact checking, with an 8B backbone achieving 88.12% accuracy and matching or surpassing GPT-4o-based program-generation baselines, which attests to the efficacy of dialectical agentic reasoning in eliciting the latent reasoning capabilities of LLMs.
CommentsEMNLP 2026 (Findings)
