HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals

• URL: http://arxiv.org/abs/2608.16353v1
• Date: Mon, 17 Aug 2026 10:03:29 GMT
• Title: HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals
• Abstract summary: We introduce HalluTracer, a framework that aggregates truthfulness evidence across every layer of the forward pass.<n>A geometric analysis reveals that the per-layer signals are weakly correlated, so that simple depth averaging suppresses layer-specific noise.<n>HalluTracer consistently outperforms matched white-box baselines.
• Score: 45.64606191137958
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Even well-aligned large language models confidently generate factually incorrect text, making hallucination a persistent reliability risk in high-stakes deployments. These models nonetheless carry linearly separable truthfulness signals in their internal representations. Existing white-box detectors, however, collapse this evidence to isolated components or a single depth, discarding discriminative information distributed across the full forward pass. We introduce HalluTracer, a detection framework that reads and aggregates truthfulness evidence across every layer of the forward pass before the model emits any answer token. A geometric analysis reveals that the per-layer signals are weakly correlated, so that simple depth averaging suppresses layer-specific noise and captures nearly all linearly accessible information. Across six open-source language models and five hallucination benchmarks, HalluTracer consistently outperforms matched white-box baselines, with gains ranging from one to fourteen points. Collectively, our work recasts hallucination detection from a layer-selection problem into a depth-aggregation problem governed by the geometric sparsity of the truthfulness signal.

Related papers

• UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations [61.85916280854257]
  Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input.<n>We introduce textbfUniProbe, a lightweight, unified, learnable detector that models a frozen LVLM's heterogeneous computational trace from a single forward pass.
  arXiv  Detail & Related papers  (2026-08-11T12:01:59Z)
• Role-Break in Attention Heads: Understanding and Detecting Hallucinations in VLMs [49.743008490747094]
  Vision-Language Models (VLMs) remain prone to hallucinations, producing content that is inconsistent with or unsupported by the input image.<n>Under a unified head-level view, we find that hallucination-induced changes manifest as localized deviations from each head's faithful contextual behavior.<n> Detailed analysis reveals that these deviations are systematically organized across attention heads, contextual sources, and deviation directions, and that the resulting signal is linearly readable once head identity is preserved.
  arXiv  Detail & Related papers  (2026-07-31T13:33:51Z)
• Grad Detect: Gradient-Based Hallucination Detection in LLMs [0.0]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, yet they remain prone to generating hallucinations.<n>We present Grad Detect, a gradient-based approach for predicting hallucinations by analyzing layer-wise gradient patterns from a single forward-backward pass during inference.<n>We evaluate Grad Detect on several Q&A benchmarks across both hallucination detection and model abstention prediction, where it consistently outperforms confidence-based and sampling-based baselines.
  arXiv  Detail & Related papers  (2026-06-23T16:46:36Z)
• TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection [22.258009855879752]
  We introduce TriLens, a detector for detecting hallucinations in language models.<n>At every layer, it reads the multi-head self-attention output, the feed-forward output, and the residual stream through the model's own logit lens.<n>The resulting 3L-dimensional trajectory describes how certainty forms across depth and across modules.
  arXiv  Detail & Related papers  (2026-05-31T05:48:21Z)
• Scalable Token-Level Hallucination Detection in Large Language Models [63.3426544914783]
  Internal hallucinations are difficult to detect in reasoning-intensive tasks.<n>We propose TokenHD, a holistic pipeline for training token-level hallucination detectors.
  arXiv  Detail & Related papers  (2026-05-12T16:47:40Z)
• Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations [32.1925100166762]
  Large vision-language models (LVLMs) achieve strong performance on visual reasoning tasks but remain highly susceptible to hallucination.<n>Existing detection methods rely on coarse, whole-image measures of how an object token relates to the input image.<n>We introduce a patch-level hallucination detection framework that examines fine-grained token-level interactions across model layers.<n>Our approach achieves up to 90% accuracy in token-level hallucination detection, demonstrating the superiority of fine-grained structural analysis for detecting hallucinations.
  arXiv  Detail & Related papers  (2026-04-06T17:07:11Z)
• 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)
• EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs [8.616813040714883]
  EigenTrack is an interpretable real-time detector for large language models (LLMs)<n>It tracks temporal shifts in representation structure that signal hallucination and OOD drift before surface errors appear.<n>Unlike existing white-box detectors, it preserves temporal context, aggregates global signals, and offers interpretable accuracy-latency trade-offs.
  arXiv  Detail & Related papers  (2025-09-19T08:05:28Z)
• Unsupervised Hallucination Detection by Inspecting Reasoning Processes [53.15199932086543]
  Unsupervised hallucination detection aims to identify hallucinated content generated by large language models (LLMs) without relying on labeled data.<n>We propose IRIS, an unsupervised hallucination detection framework, leveraging internal representations intrinsic to factual correctness.<n>Our approach is fully unsupervised, computationally low cost, and works well even with few training data, making it suitable for real-time detection.
  arXiv  Detail & Related papers  (2025-09-12T06:58:17Z)

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.