(Im)possibility of Automated Hallucination Detection in Large Language Models

• URL: http://arxiv.org/abs/2504.17004v1
• Date: Wed, 23 Apr 2025 18:00:07 GMT
• Title: (Im)possibility of Automated Hallucination Detection in Large Language Models
• Authors: Amin Karbasi, Omar Montasser, John Sous, Grigoris Velegkas,
• Abstract summary: We introduce a theoretical framework to analyze the feasibility of automatically detecting hallucinations produced by large language models (LLMs)<n>We investigate whether an algorithm, trained on examples drawn from an unknown target language, can reliably determine whether the LLM's outputs are correct or constitute hallucinations.<n>We show that the use of expert-labeled feedback, i.e., training the detector with both positive examples (correct statements) and negative examples (explicitly labeled incorrect statements) dramatically changes this conclusion.
• Score: 40.13262095901877
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Is automated hallucination detection possible? In this work, we introduce a theoretical framework to analyze the feasibility of automatically detecting hallucinations produced by large language models (LLMs). Inspired by the classical Gold-Angluin framework for language identification and its recent adaptation to language generation by Kleinberg and Mullainathan, we investigate whether an algorithm, trained on examples drawn from an unknown target language $K$ (selected from a countable collection) and given access to an LLM, can reliably determine whether the LLM's outputs are correct or constitute hallucinations. First, we establish an equivalence between hallucination detection and the classical task of language identification. We prove that any hallucination detection method can be converted into a language identification method, and conversely, algorithms solving language identification can be adapted for hallucination detection. Given the inherent difficulty of language identification, this implies that hallucination detection is fundamentally impossible for most language collections if the detector is trained using only correct examples from the target language. Second, we show that the use of expert-labeled feedback, i.e., training the detector with both positive examples (correct statements) and negative examples (explicitly labeled incorrect statements), dramatically changes this conclusion. Under this enriched training regime, automated hallucination detection becomes possible for all countable language collections. These results highlight the essential role of expert-labeled examples in training hallucination detectors and provide theoretical support for feedback-based methods, such as reinforcement learning with human feedback (RLHF), which have proven critical for reliable LLM deployment.

Related papers

• ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries [29.561699707926056]
  Large language models (LLMs) are prone to hallucination-outputs that stray from intended meanings.<n>We introduce a first-of-its-kind dataset with $sim$10K samples, curated specifically for hallucination detection in code summarization.
  arXiv  Detail & Related papers  (2024-10-17T19:38:55Z)
• Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps [48.58310785625051]
  Large language models (LLMs) can hallucinate details and respond with unsubstantiated answers. This paper describes a simple approach for detecting such contextual hallucinations.
  arXiv  Detail & Related papers  (2024-07-09T17:44:34Z)
• 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)
• Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback [40.930238150365795]
  We propose detecting and mitigating hallucinations in Large Vision Language Models (LVLMs) via fine-grained AI feedback.<n>We generate a small-size hallucination annotation dataset by proprietary models.<n>Then, we propose a detect-then-rewrite pipeline to automatically construct preference dataset for training hallucination mitigating model.
  arXiv  Detail & Related papers  (2024-04-22T14:46:10Z)
• Comparing Hallucination Detection Metrics for Multilingual Generation [62.97224994631494]
  This paper assesses how well various factual hallucination detection metrics identify hallucinations in generated biographical summaries across languages. We compare how well automatic metrics correlate to each other and whether they agree with human judgments of factuality. Our analysis reveals that while the lexical metrics are ineffective, NLI-based metrics perform well, correlating with human annotations in many settings and often outperforming supervised models.
  arXiv  Detail & Related papers  (2024-02-16T08:10:34Z)
• Hallucinations in Neural Automatic Speech Recognition: Identifying Errors and Hallucinatory Models [11.492702369437785]
  Hallucinations are semantically unrelated to the source utterance, yet still fluent and coherent. We show that commonly used metrics, such as word error rates, cannot differentiate between hallucinatory and non-hallucinatory models. We devise a framework for identifying hallucinations by analysing their semantic connection with the ground truth and their fluency.
  arXiv  Detail & Related papers  (2024-01-03T06:56:56Z)
• 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)
• Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations [3.9566468090516067]
  Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. LLMs are prone to generate hallucinations that are not supported by the provided sources. We propose a hierarchical framework to detect and mitigate such ungrounded hallucination.
  arXiv  Detail & Related papers  (2023-10-06T00:10:46Z)
• AutoHall: Automated Hallucination Dataset Generation for Large Language Models [56.92068213969036]
  This paper introduces a method for automatically constructing model-specific hallucination datasets based on existing fact-checking datasets called AutoHall. We also propose a zero-resource and black-box hallucination detection method based on self-contradiction.
  arXiv  Detail & Related papers  (2023-09-30T05:20:02Z)
• Zero-Resource Hallucination Prevention for Large Language Models [45.4155729393135]
  "Hallucination" refers to instances where large language models (LLMs) generate factually inaccurate or ungrounded information. We introduce a novel pre-language self-evaluation technique, referred to as SELF-FAMILIARITY, which focuses on evaluating the model's familiarity with the concepts present in the input instruction. We validate SELF-FAMILIARITY across four different large language models, demonstrating consistently superior performance compared to existing techniques.
  arXiv  Detail & Related papers  (2023-09-06T01:57:36Z)

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.