A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs

• URL: http://arxiv.org/abs/2505.08200v1
• Date: Tue, 13 May 2025 03:30:26 GMT
• Title: A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs
• Authors: Artem Shelmanov, Ekaterina Fadeeva, Akim Tsvigun, Ivan Tsvigun, Zhuohan Xie, Igor Kiselev, Nico Daheim, Caiqi Zhang, Artem Vazhentsev, Mrinmaya Sachan, Preslav Nakov, Timothy Baldwin,
• Abstract summary: Large Language Models (LLMs) have the tendency to hallucinate, i.e., to sporadically generate false or fabricated information.<n>Uncertainty quantification (UQ) provides a framework for assessing the reliability of model outputs.<n>We pre-train a collection of UQ heads for popular LLM series, including Mistral, Llama, and Gemma 2.
• Score: 71.97006967209539
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have the tendency to hallucinate, i.e., to sporadically generate false or fabricated information. This presents a major challenge, as hallucinations often appear highly convincing and users generally lack the tools to detect them. Uncertainty quantification (UQ) provides a framework for assessing the reliability of model outputs, aiding in the identification of potential hallucinations. In this work, we introduce pre-trained UQ heads: supervised auxiliary modules for LLMs that substantially enhance their ability to capture uncertainty compared to unsupervised UQ methods. Their strong performance stems from the powerful Transformer architecture in their design and informative features derived from LLM attention maps. Experimental evaluation shows that these heads are highly robust and achieve state-of-the-art performance in claim-level hallucination detection across both in-domain and out-of-domain prompts. Moreover, these modules demonstrate strong generalization to languages they were not explicitly trained on. We pre-train a collection of UQ heads for popular LLM series, including Mistral, Llama, and Gemma 2. We publicly release both the code and the pre-trained heads.

Related papers

• Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor [18.9616029343245]
  hallucinations generated by large language models (LLMs) undermine the credibility of intelligent agents.<n>HalMit is a novel black-box watchdog framework that models the generalization bound of LLM-empowered agents.
  arXiv  Detail & Related papers  (2025-07-21T09:08:58Z)
• UQLM: A Python Package for Uncertainty Quantification in Large Language Models [0.0]
  We introduce UQLM, a Python package for hallucination detection using state-of-the-art uncertainty quantification (UQ) techniques.<n>This toolkit offers a suite of UQ-based scorers that compute response-level confidence scores ranging from 0 to 1.
  arXiv  Detail & Related papers  (2025-07-08T17:22:32Z)
• Uncertainty-Aware Attention Heads: Efficient Unsupervised Uncertainty Quantification for LLMs [114.46334319795785]
  Large language models (LLMs) exhibit impressive fluency, but often produce critical errors known as "hallucinations"<n>We propose RAUQ (Recurrent Attention-based Uncertainty Quantification), an unsupervised approach that leverages intrinsic attention patterns in transformers to detect hallucinations efficiently.<n> Experiments across 4 LLMs and 12 question answering, summarization, and translation tasks demonstrate that RAUQ yields excellent results.
  arXiv  Detail & Related papers  (2025-05-26T14:28:37Z)
• Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models [0.0]
  Hallucinations in large language models (LLMs) present a growing challenge across real-world applications.<n>We propose a prompt-based framework to systematically trigger and quantify hallucination.
  arXiv  Detail & Related papers  (2025-05-01T14:33:47Z)
• DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations [14.025772159366184]
  Large Language Models (LLMs) often hallucinate, producing unfaithful or factually incorrect outputs. Recent studies have identified specific attention heads within the Transformer architecture, known as retrieval heads. We propose Decoding by Contrasting Retrieval Heads (DeCoRe), a novel training-free decoding strategy.
  arXiv  Detail & Related papers  (2024-10-24T15:44:33Z)
• Mitigating Entity-Level Hallucination in Large Language Models [11.872916697604278]
  This paper proposes Dynamic Retrieval Augmentation based on hallucination Detection (DRAD) as a novel method to detect and mitigate hallucinations in Large Language Models (LLMs) Experiment results show that DRAD demonstrates superior performance in both detecting and mitigating hallucinations in LLMs.
  arXiv  Detail & Related papers  (2024-07-12T16:47:34Z)
• Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models [70.19081534515371]
  Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks. They generate unfaithful or inconsistent content that deviates from the input source, leading to severe consequences. We propose a robust discriminator named RelD to effectively detect hallucination in LLMs' generated answers.
  arXiv  Detail & Related papers  (2024-07-04T18:47:42Z)
• Unfamiliar Finetuning Examples Control How Language Models Hallucinate [75.03210107477157]
  Large language models are known to hallucinate when faced with unfamiliar queries. We find that unfamiliar examples in the models' finetuning data are crucial in shaping these errors. Our work further investigates RL finetuning strategies for improving the factuality of long-form model generations.
  arXiv  Detail & Related papers  (2024-03-08T18:28:13Z)
• HypoTermQA: Hypothetical Terms Dataset for Benchmarking Hallucination Tendency of LLMs [0.0]
  Hallucinations pose a significant challenge to the reliability and alignment of Large Language Models (LLMs) This paper introduces an automated scalable framework that combines benchmarking LLMs' hallucination tendencies with efficient hallucination detection. The framework is domain-agnostic, allowing the use of any language model for benchmark creation or evaluation in any domain.
  arXiv  Detail & Related papers  (2024-02-25T22:23:37Z)
• Alleviating Hallucinations of Large Language Models through Induced Hallucinations [67.35512483340837]
  Large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information. We propose a simple textitInduce-then-Contrast Decoding (ICD) strategy to alleviate hallucinations.
  arXiv  Detail & Related papers  (2023-12-25T12:32:49Z)
• Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus [99.33091772494751]
  Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields. LLMs are prone to hallucinate untruthful or nonsensical outputs that fail to meet user expectations. We propose a novel reference-free, uncertainty-based method for detecting hallucinations in LLMs.
  arXiv  Detail & Related papers  (2023-11-22T08:39:17Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.