FacTool: Factuality Detection in Generative AI - A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios
By Ethan Chern, Steffi Chern, Shiqi Chen, Weizhe Yuan, Kehua Feng, Chunting Zhou, Junxian He, Graham Neubig, Pengfei Liu. arXiv.org, 2023
315 citations recorded by the source corpus.
The emergence of generative pre-trained models has facilitated the synthesis of high-quality text, but it has also posed challenges in identifying factual errors in the generated text. In particular: (1) A wider range of tasks now face an increasing risk of containing factual errors when handled by generative models. (2) Generated texts tend to be lengthy and lack a clearly defined granularity for individual facts. (3) There is a scarcity of explicit evidence available during the process of fact checking. With the above challenges in mind, in this paper, we propose FacTool, a task and domain agnostic framework for detecting factual errors of texts generated by large language models (e.g., ChatGPT). Experiments on four different tasks (knowledge-based QA, code generation, mathematical reasoning, and scientific literature review) show the efficacy of the proposed method. We release the code of FacTool associated with ChatGPT plugin interface at https://github.com/GAIR-NLP/factool .
Subfields: Artificial Intelligence, Computational Theory and Mathematics
View Paper: https://www.semanticscholar.org/paper/7a5b44ea10a51708e18786595c8d70b18950da11
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Tool learning with large language models: a survey (2024, unknown): “The remaining part of this paper (as illustrated in Figure 2) is organized as follows: We begin by introducing the foundational concepts and terminology related to tool learning (§2).”
- Knowledge Conflicts for LLMs: A Survey (2024, unknown): “General models, such as Chern et al. (2023)’s fact-checking framework, integrate LLMs with various tools to detect factual errors.”
- Toward expert-level medical question answering with large language models (2025, unknown): “It is distinct from retrieval-augmented generation approaches that leverage a fixed corpus and embedding space to find documents to condition LLM generations on 58 , and is most similar to other approaches that break down verification of claims into multiple steps 59,60 .”
- RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models (2023, background): “Retrieval-augmented generation (RAG) is extensively used to supply LLMs with updated, relevant knowledge, significantly mitigating hal-064 lucination (Varshney et al., 2023).”
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions (2023, unknown): “In a broader perspective, Chern et al. (2023) proposed a unified framework that enables LLMs to detect factual errors by leveraging a suite of external tools for evidence collection.”
- LLM as a Broken Telephone: Iterative Generation Distorts Information (2025, unknown): “Existing research predominantly relies on metrics such as token similarity (Hu and Zhou, 2024), output diversity (Guo et al., 2024a; Shaib et al., 2024), and factuality (Wang et al., 2023; Iqbal et al., 2024; Min et al., 2023; Chern et al., 2023).”