STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models

• URL: http://arxiv.org/abs/2604.03045v1
• Date: Fri, 03 Apr 2026 13:52:57 GMT
• Title: STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models
• Abstract summary: Large Video Language Models (Video-LLMs) are prone to hallucinations, often generating visually unsupported or incorrect temporal relations.<n>We propose STEAR, which identifies high-risk decoding steps and selects token-conditioned visual evidence from grounding-aware middle layers.<n>Experiments demonstrate that STEAR consistently reduces hallucinations while improving temporal consistency, faithfulness, and robustness.
• Score: 14.848157882117613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video Large Language Models (Video-LLMs) remain prone to spatiotemporal hallucinations, often generating visually unsupported details or incorrect temporal relations. Existing mitigation methods typically treat hallucination as a uniform decoding failure, applying globally shared correction rules. We instead observe that decoder layers contribute differently to visual grounding and later linguistic composition, indicating that intervention must be layer-aware. Based on this insight, we propose STEAR, a layer-aware spatiotemporal evidence intervention framework. STEAR identifies high-risk decoding steps and selects token-conditioned visual evidence from grounding-sensitive middle layers. It uses this shared evidence for two coupled purposes: restoring missing local grounding in middle layers, and constructing temporally perturbed patch-level counterfactuals to falsify inconsistent reasoning during late-layer decoding. Consequently, STEAR mitigates both spatial and temporal hallucinations within an efficient single-encode inference framework. Experiments across representative Video-LLM backbones and challenging benchmarks demonstrate that STEAR consistently reduces hallucinations while improving faithfulness, temporal consistency, and robustness. Our results confirm that reliable video decoding relies on intervening on precise evidence at the right layer, rather than enforcing a global penalty. The code is provided in the Supplementary Material.

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)
• Look Clearly Before Answering: Mitigating Hallucinations in LVLMs via Saliency-Driven Perceptual Realignment [45.92240827409312]
  Saliency-Driven Perceptual Realignment (SDPR) is a training-free framework that mitigates the degradation of visual awareness throughout inference.<n>Our proposed SDPR is robust against hallucinations due to its holistic alignment of visual awareness across the entire generative trajectory.
  arXiv  Detail & Related papers  (2026-07-18T14:39:16Z)
• See Only When Needed: Context-Aware Attention Intervention for Mitigating Hallucinations in LVLMs [81.71384150441163]
  We propose Context-aware Attention Intervention (CAI) for large vision-language models (LVLMs)<n>CAI enforces a see only when needed principle via two-axis selectivity: where to look and when to intervene.<n> experiments across multiple LVLM backbones and benchmarks show that CAI achieves state-of-the-art hallucination mitigation.
  arXiv  Detail & Related papers  (2026-06-29T06:35:47Z)
• YARD: Y-Architecture Register Decoding for Efficient Hallucination Mitigation in Large Vision-Language Models [16.521294712284813]
  Contrastive decoding (CD) seeks to mitigate hallucinations in Large Vision-Language Models (LVLMs) by contrasting the output distributions of a standard model and a visually degraded model.<n>Existing training-free CD methods suffer from sub-optimal degraded branches.<n>We propose YARD, a training-free Y-Architecture Register Decoding framework.
  arXiv  Detail & Related papers  (2026-05-29T15:23:39Z)
• Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models [154.39583176906893]
  Large language models (MLs) have advanced understanding, they remain highly prone to hallucinations in scenes.<n>We argue this stems from a failure intemporal monitoring, the ability to persistently track object dynamic identities, states, and relations over time.<n>Existing benchmarks obscure this deficit relying on single final-answer queries that can often be resolved via local visual cues or statistical priors.
  arXiv  Detail & Related papers  (2026-05-09T14:32:36Z)
• Relaxing Anchor-Frame Dominance for Mitigating Hallucinations in Video Large Language Models [22.554751069064906]
  Recent Video Large Language Models (Video-LLMs) have demonstrated strong capability in video understanding, yet they still suffer from hallucinations.<n>We investigate a decoder-side phenomenon in which the model exhibits a temporally imbalanced concentration pattern.<n>We propose Decoder-side Temporal Rebalancing (DTR), a training-free, layer-selective inference method that rebalances temporal evidence allocation in middle-to-late decoder layers.
  arXiv  Detail & Related papers  (2026-04-14T11:05:42Z)
• SAGE: Sink-Aware Grounded Decoding for Multimodal Hallucination Mitigation [33.381194425912234]
  Large vision-language models (VLMs) frequently suffer from hallucinations, generating content that is inconsistent with visual inputs.<n>We introduce SAGE, a Sink-Aware Grounded Decoding framework that mitigates hallucinations by dynamically modulating self-attention during generation.<n>Our method achieves an average relative improvement of 10.65% on MSCOCO and 7.19% on AMBER across diverse VLM architectures.
  arXiv  Detail & Related papers  (2026-03-29T22:52:03Z)
• INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs [69.11382230669491]
  hallucinations are outputs that contradict either video evidence (faithfulness) or verifiable world knowledge (factuality)<n>textscINFACT evaluates models in four modes: Base (clean), Visual Degradation, Evidence, and Temporal Intervention for order-sensitive items.<n>Experiments on 14 representative Video-LLMs reveal that higher Base-mode accuracy does not reliably translate to higher reliability in the induced modes.
  arXiv  Detail & Related papers  (2026-03-12T03:03:16Z)
• MACD: Model-Aware Contrastive Decoding via Counterfactual Data [0.0]
  Video language models (Video-LLMs) are prone to hallucinations, often generating plausible but ungrounded content when visual evidence is weak, ambiguous, or biased.<n>We propose Model-aware Counterfactual Data based Contrastive Decoding (MACD), a new inference strategy that combines model-guided counterfactual construction with decoding.<n>Our approach uses the Video-LLM's own feedback to identify object regions most responsible for hallucination, generating targeted counterfactual inputs at the object level rather than arbitrary frame or temporal modifications.
  arXiv  Detail & Related papers  (2026-02-02T07:21:02Z)
• SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding [30.820850789099932]
  We propose a training-free method that adaptively enhances temporal and spatial faithfulness for each output token.<n>SEASON outperforms all existing training-free hallucination mitigation approaches on three hallucination examination benchmarks.
  arXiv  Detail & Related papers  (2025-12-04T10:17:20Z)
• ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding [61.526407756322264]
  We introduce ELV-Halluc, the first benchmark dedicated to long-video hallucination.<n>We find that models are more prone to SAH on rapidly changing semantics.<n>We also achieve improvements on both ELV-Halluc and Video-MME.
  arXiv  Detail & Related papers  (2025-08-29T10:25:03Z)
• Context-aware TFL: A Universal Context-aware Contrastive Learning Framework for Temporal Forgery Localization [60.73623588349311]
  We propose a universal context-aware contrastive learning framework (UniCaCLF) for temporal forgery localization.<n>Our approach leverages supervised contrastive learning to discover and identify forged instants by means of anomaly detection.<n>An efficient context-aware contrastive coding is introduced to further push the limit of instant feature distinguishability between genuine and forged instants.
  arXiv  Detail & Related papers  (2025-06-10T06:40:43Z)
• Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models [3.9464481148889354]
  We propose a novel decoding mechanism, Decoding with Inter-layer Consistency via Layer Aggregation (DCLA)<n>Our approach constructs a dynamic semantic reference by aggregating representations from previous layers, and corrects semantically deviated layers to enforce inter-layer consistency.<n> Experiments on hallucination benchmarks such as MME and POPE demonstrate that DCLA effectively reduces hallucinations while enhancing the reliability and performance of LVLMs.
  arXiv  Detail & Related papers  (2025-05-18T10:15:42Z)
• Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling [78.78822033285938]
  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)

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.