A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations

• URL: http://arxiv.org/abs/2507.23221v1
• Date: Thu, 31 Jul 2025 03:26:57 GMT
• Title: A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations
• Authors: Charles O'Neill, Slava Chalnev, Chi Chi Zhao, Max Kirkby, Mudith Jayasekara,
• Abstract summary: A generator-agnostic observer model detects hallucinations via a single forward pass and a linear probe on its residual stream.<n>This probe isolates a single, linear direction separating hallucinated from faithful text, outperforming baselines by 5-27 points.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contextual hallucinations -- statements unsupported by given context -- remain a significant challenge in AI. We demonstrate a practical interpretability insight: a generator-agnostic observer model detects hallucinations via a single forward pass and a linear probe on its residual stream. This probe isolates a single, transferable linear direction separating hallucinated from faithful text, outperforming baselines by 5-27 points and showing robust mid-layer performance across Gemma-2 models (2B to 27B). Gradient-times-activation localises this signal to sparse, late-layer MLP activity. Critically, manipulating this direction causally steers generator hallucination rates, proving its actionability. Our results offer novel evidence of internal, low-dimensional hallucination tracking linked to specific MLP sub-circuits, exploitable for detection and mitigation. We release the 2000-example ContraTales benchmark for realistic assessment of such solutions.

Related papers

• Hallucination Begins Where Saliency Drops [18.189047289404325]
  hallucinations frequently arise when preceding output tokens exhibit low saliency toward the prediction of the next token.<n>We introduce LVLMs-Saliency, a gradient-aware diagnostic framework that quantifies the visual grounding strength of each output token.<n>Our method significantly reduces hallucination rates while preserving fluency and task performance, offering a robust and interpretable solution.
  arXiv  Detail & Related papers  (2026-01-28T05:50:52Z)
• A novel hallucination classification framework [0.0]
  This work introduces a novel methodology for the automatic detection of hallucinations generated during large language model (LLM) inference.<n>The proposed approach is based on a systematic taxonomy and controlled reproduction of diverse hallucination types through prompt engineering.
  arXiv  Detail & Related papers  (2025-10-06T09:54:20Z)
• Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations [73.37711261605271]
  hallucination mitigation methods are mainly based on preference alignment and require external human annotations or auxiliary models for preference data collection.<n>We propose Autonomous Preference Alignment via Self-Injection (APASI), a novel and generalizable method that mitigates hallucinations without external dependencies.<n>APASI leverages the target LVLM to self-inject hallucinations into a generated response, creating a pair of responses with varying preference levels.
  arXiv  Detail & Related papers  (2025-09-14T14:26:53Z)
• 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)
• Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models [0.0]
  We propose Counterfactual Probing, a novel approach for detecting and mitigating hallucinations in large language models.<n>Our method dynamically generates counterfactual statements that appear plausible but contain subtle factual errors, then evaluates the model's sensitivity to these perturbations.
  arXiv  Detail & Related papers  (2025-08-03T17:29:48Z)
• ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs [50.18087419133284]
  hallucination detection methods leveraging hidden states predominantly focus on static and isolated representations.<n>We introduce a novel metric, the ICR Score, which quantifies the contribution of modules to the hidden states' update.<n>We propose a hallucination detection method, the ICR Probe, which captures the cross-layer evolution of hidden states.
  arXiv  Detail & Related papers  (2025-07-22T11:44:26Z)
• HIDE and Seek: Detecting Hallucinations in Language Models via Decoupled Representations [17.673293240849787]
  Contemporary Language Models (LMs) often generate content that is factually incorrect or unfaithful to the input context.<n>We propose a single-pass, training-free approach for effective Hallucination detectIon via Decoupled rEpresentations (HIDE)<n>Our results demonstrate that HIDE outperforms other single-pass methods in almost all settings.
  arXiv  Detail & Related papers  (2025-06-21T16:02:49Z)
• Attention Head Embeddings with Trainable Deep Kernels for Hallucination Detection in LLMs [47.18623962083962]
  We present a novel approach for detecting hallucinations in large language models.<n>We find that hallucinated responses exhibit smaller deviations from their prompts compared to grounded responses.<n>We propose a model-intrinsic detection method that uses distributional distances as principled hallucination scores.
  arXiv  Detail & Related papers  (2025-06-11T15:59:15Z)
• Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations [25.18901449626428]
  A widely adopted strategy to detect hallucination, known as self-assessment, relies on the model's own output confidence to estimate the factual accuracy of its answers.<n>We propose Sample-Specific Prompting (SSP), a new framework that improves self-assessment by analyzing perturbation sensitivity at intermediate representations.<n>SSP significantly outperforms prior methods across a range of hallucination detection benchmarks.
  arXiv  Detail & Related papers  (2025-06-03T09:44:28Z)
• MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM [58.2298313720146]
  Multimodal hallucinations are multi-sourced and arise from diverse causes.<n>Existing benchmarks fail to adequately distinguish between perception-induced hallucinations and reasoning-induced hallucinations.
  arXiv  Detail & Related papers  (2025-05-30T05:54:36Z)
• HalluLens: LLM Hallucination Benchmark [49.170128733508335]
  Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as "hallucination"<n>This paper introduces a comprehensive hallucination benchmark, incorporating both new extrinsic and existing intrinsic evaluation tasks.
  arXiv  Detail & Related papers  (2025-04-24T13:40:27Z)
• Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling [67.14942827452161]
  Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations.<n>In this work, we introduce REVERSE, a unified framework that integrates hallucination-aware training with on-the-fly self-verification.
  arXiv  Detail & Related papers  (2025-04-17T17:59:22Z)
• Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations [82.42811602081692]
  This paper introduces a subsequence association framework to systematically trace and understand hallucinations.<n>Key insight is hallucinations that arise when dominant hallucinatory associations outweigh faithful ones.<n>We propose a tracing algorithm that identifies causal subsequences by analyzing hallucination probabilities across randomized input contexts.
  arXiv  Detail & Related papers  (2025-04-17T06:34:45Z)
• Hallucination Detection in LLMs with Topological Divergence on Attention Graphs [64.74977204942199]
  Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models.<n>We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting.
  arXiv  Detail & Related papers  (2025-04-14T10:06:27Z)
• Robust Hallucination Detection in LLMs via Adaptive Token Selection [25.21763722332831]
  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)
• 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)
• 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)

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.