Papers
arxiv:2510.19318

HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy

Published on Oct 22, 2025
Authors:
,
,
,
,
,
,
,
,

Abstract

A comprehensive hallucination taxonomy and HAD models unify detection, span-level identification, and correction in one inference process, trained on synthetic data, and achieve state-of-the-art results on multiple benchmarks.

The increasing reliance on natural language generation (NLG) models, particularly large language models, has raised concerns about the reliability and accuracy of their outputs. A key challenge is hallucination, where models produce plausible but incorrect information. As a result, hallucination detection has become a critical task. In this work, we introduce a comprehensive hallucination taxonomy with 11 categories across various NLG tasks and propose the HAllucination Detection (HAD) models https://github.com/pku0xff/HAD, which integrate hallucination detection, span-level identification, and correction into a single inference process. Trained on an elaborate synthetic dataset of about 90K samples, our HAD models are versatile and can be applied to various NLG tasks. We also carefully annotate a test set for hallucination detection, called HADTest, which contains 2,248 samples. Evaluations on in-domain and out-of-domain test sets show that our HAD models generally outperform the existing baselines, achieving state-of-the-art results on HaluEval, FactCHD, and FaithBench, confirming their robustness and versatility.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2510.19318
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2510.19318 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2510.19318 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2510.19318 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.