← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-demo.36 · 记录 #1
FactSearch: An Interactive Agentic Fact Search System for Verifying Large Language Model Outputs
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 22:08
摘要
Large language models (LLMs) frequently generate factually incorrect or unverifiable statements, motivating tool-augmented verification systems that combine model reasoning with external evidence retrieval. For factuality evaluation to be scientifically reliable, verification pipelines must be controllable and reproducible: retrieval configuration and reasoning behaviour should be explicitly configurable and stable across runs. In practice, many existing systems depend on commercial search APIs whose ranking policies and retrieval behaviours are opaque and externally controlled, introducing uncontrolled variability into evaluation. This makes it difficult to disentangle reasoning errors from retrieval effects. We present FactSearch, a reproducibility-oriented agentic fact search system for claim-level factuality verification, built on a locally aggregated open-source search infrastructure. FactSearch follows an agentic verification workflow: it decomposes model outputs into atomic factual claims, generates targeted search queries, retrieves supporting evidence via a self-hosted meta-search engine, and performs modular verification within a fully configurable pipeline. By treating retrieval infrastructure as a first-class component, the system enables systematic analysis of retrieval–reasoning interactions. An interactive web interface supports transparent inspection and practical deployment. The project is available at https://factsearch.github.io.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
FactSearch: An Interactive Agentic Fact Search System for Verifying Large Language Model Outputs
Large language models (LLMs) frequently generate factually incorrect or unverifiable statements, motivating tool-augmented verification systems that combine model reasoning with external evidence retrieval. For factuality evaluation to be scientifically reliable, verification pipelines must be controllable and reproducible: retrieval configuration and reasoning behaviour should be explicitly configurable and stable across runs. In practice, many existing systems depend on commercial search APIs whose ranking policies and retrieval behaviours are opaque and externally controlled, introducing uncontrolled variability into evaluation. This makes it difficult to disentangle reasoning errors from retrieval effects. We present FactSearch, a reproducibility-oriented agentic fact search system for claim-level factuality verification, built on a locally aggregated open-source search infrastructure. FactSearch follows an agentic verification workflow: it decomposes model outputs into atomic factual claims, generates targeted search queries, retrieves supporting evidence via a self-hosted meta-search engine, and performs modular verification within a fully configurable pipeline. By treating retrieval infrastructure as a first-class component, the system enables systematic analysis of retrieval–reasoning interactions. An interactive web interface supports transparent inspection and practical deployment. The project is available at https://factsearch.github.io.
查看此版本解读 →查看此版本原文 ↗