Scalable Token-Level Hallucination Detection in Large Language Models

• URL: http://arxiv.org/abs/2605.12384v1
• Date: Tue, 12 May 2026 16:47:40 GMT
• Title: Scalable Token-Level Hallucination Detection in Large Language Models
• Abstract summary: Internal hallucinations are difficult to detect in reasoning-intensive tasks.<n>We propose TokenHD, a holistic pipeline for training token-level hallucination detectors.
• Score: 63.3426544914783
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have demonstrated remarkable capabilities, but they still frequently produce hallucinations. These hallucinations are difficult to detect in reasoning-intensive tasks, where the content appears coherent but contains errors like logical flaws and unreliable intermediate results. While step-level analysis is commonly used to detect internal hallucinations, it suffers from limited granularity and poor scalability due to its reliance on step segmentation. To address these limitations, we propose TokenHD, a holistic pipeline for training token-level hallucination detectors. Specifically, TokenHD consists of a scalable data engine for synthesizing large-scale hallucination annotations along with a training recipe featuring an importance-weighted strategy for robust model training. To systematically assess the detection performance, we also provide a rigorous evaluation protocol. Through training within TokenHD, our detector operates directly on free-form text to identify hallucinations, eliminating the need for predefined step segmentation or additional text reformatting. Our experiments show that even a small detector (0.6B) achieves substantial performance gains after training, surpassing much larger reasoning models (e.g., QwQ-32B), and detection performance scales consistently with model size from 0.6B to 8B. Finally, we show that our detector can generalize well across diverse practical scenarios and explore strategies to further enhance its cross-domain generalization capability.

Related papers

• TRE: Training-Free Hallucination Detection for Diffusion Language Models [9.622962795441852]
  We propose TRE, a training-free hallucination detection metric for D-LLMs.<n> TRE estimates hallucination risk directly from the entropy signals of a single generation, without requiring any detector training or repeated sampling.<n>Extensive experiments on multiple D-LLMs and QA datasets demonstrate that TRE achieves competitive performance, while enjoying strong generalizability, efficiency, and robustness.
  arXiv  Detail & Related papers  (2026-06-29T00:47:48Z)
• Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps [1.8825446478246406]
  Hallucinations in Speech Large Language Models (SpeechLLMs) pose significant risks, yet existing detection methods rely on gold-standard outputs that are costly or impractical to obtain.<n>We investigate four attention-derived metrics: AUDIORATIO, AUDIOCONSISTENCY, AUDIOENTROPY, and TEXTENTROPY, designed to capture pathological attention patterns associated with hallucination.<n>Across automatic speech recognition and speech-to-text translation tasks, our approach outperforms uncertainty-based and prior attention-based baselines.
  arXiv  Detail & Related papers  (2026-04-21T15:18:10Z)
• DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning [48.77865928715759]
  Diffusion large language models (D-LLMs) have emerged as a promising alternative to auto-regressive models.<n> hallucination remains a critical issue that hinders their reliability.<n>We propose DynHD that bridge these gaps from both spatial (token sequence) and temporal (denoising dynamics) perspectives.
  arXiv  Detail & Related papers  (2026-03-17T12:40:29Z)
• Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph [12.233570103035312]
  We propose a semantic-level internal reasoning graph-based method for detecting faithfulness hallucinations.<n>Our method achieves better overall performance compared to state-of-the-art baselines on RAGTruth and Dolly-15k.
  arXiv  Detail & Related papers  (2026-01-06T14:35:20Z)
• PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning [87.35309934860938]
  hallucinations in large language models (MLLMs) are strongly associated with insufficient attention allocated to visual tokens.<n>We propose textbfPruneHal, a training-free, simple yet effective method that leverages adaptive KV cache pruning to enhance the model's focus on critical visual information.
  arXiv  Detail & Related papers  (2025-10-22T02:41:07Z)
• SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs [52.03164192840023]
  Large Vision-Language Models (LVLMs) still suffer from hallucinations, i.e., generating content inconsistent with input or established world knowledge.<n>We propose an automated data construction pipeline that produces scalable, controllable, and diverse evaluation data.<n>We construct SHALE, a benchmark designed to assess both faithfulness and factuality hallucinations.
  arXiv  Detail & Related papers  (2025-08-13T07:58:01Z)
• Robust Hallucination Detection in LLMs via Adaptive Token Selection [35.06045656558144]
  Hallucinations in large language models (LLMs) pose significant safety concerns that impede their broader deployment.<n>We propose HaMI, a novel approach that enables robust detection of hallucinations through adaptive selection and learning of critical tokens.<n>We achieve this robustness by an innovative formulation of the Hallucination detection task as Multiple Instance (HaMI) learning over token-level representations within a sequence.
  arXiv  Detail & Related papers  (2025-04-10T15:39:10Z)
• CHAIR -- Classifier of Hallucination as Improver [1.397828249435483]
  We introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for detecting hallucinations by analyzing internal logits from each layer of every token.<n>Our method extracts a compact set of features such as maximum, minimum, mean, standard deviation, and slope-from the token logits across all layers, enabling effective hallucination detection without overfitting.
  arXiv  Detail & Related papers  (2025-01-05T12:15:02Z)
• 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)
• A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection [63.56136319976554]
  Large Language Models (LLMs) generate hallucinations, which can cause significant damage when deployed for mission-critical tasks. We propose a self-check approach based on reverse validation to detect factual errors automatically in a zero-resource fashion. We empirically evaluate our method and existing zero-resource detection methods on two datasets.
  arXiv  Detail & Related papers  (2023-10-10T10:14:59Z)
• Detecting Hallucinated Content in Conditional Neural Sequence Generation [165.68948078624499]
  We propose a task to predict whether each token in the output sequence is hallucinated (not contained in the input) We also introduce a method for learning to detect hallucinations using pretrained language models fine tuned on synthetic data.
  arXiv  Detail & Related papers  (2020-11-05T00:18:53Z)

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.