Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering

• URL: http://arxiv.org/abs/2605.29881v1
• Date: Thu, 28 May 2026 13:07:01 GMT
• Title: Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering
• Abstract summary: Large vision-language models (LVLMs) often hallucinate objects that are not present in the input image.<n>Existing inference-time mitigation methods modify logits or hidden states throughout generation.<n>They lack an explicit grounding objective, intervene even when the model is already well-grounded, and use fixed correction strengths that do not adapt to the severity of grounding failure.<n>We propose BRACS, a training-free steering framework that addresses these issues through barrier-regulated adaptive closed-form steering.
• Score: 2.497926557563177
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large vision-language models (LVLMs) often hallucinate objects that are not present in the input image, largely because visual grounding weakens as decoding progresses. Existing inference-time mitigation methods modify logits or hidden states throughout generation, but they suffer from three key limitations: they lack an explicit grounding objective, intervene even when the model is already well-grounded, and use fixed correction strengths that do not adapt to the severity of grounding failure. We propose BRACS (Barrier-Regulated Adaptive Closed-form Steering), a training-free steering framework that addresses these issues through barrier-regulated adaptive closed-form steering. BRACS monitors the model's own attention to measure visual grounding and applies corrections to the hidden states only when grounding deteriorates. The corrective update is computed analytically in closed form, requiring no training of auxiliary networks or model retraining. Experiments on LLaVA-1.5-7B and Qwen-VL-Chat show that BRACS consistently outperforms prior methods on hallucination benchmarks, reducing CHAIR$_s$ by 9.4 points and improving POPE F1 by 2.7 points, while matching or improving performance on four general multimodal benchmarks. BRACS also remains efficient, operating at 80% of greedy decoding throughput and achieving 1.3 times higher speed on average than the baselines.

Related papers

• ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models [23.3892541362594]
  PROBEACT is a training-free runtime intervention frame-6 work.<n>It detects and recovers from grasping and placement failures in pre-7 trained VLA policies.
  arXiv  Detail & Related papers  (2026-06-08T17:04:24Z)
• P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization [55.74731799669337]
  Hallucination has recently garnered significant research attention in Large Vision-Language Models (LVLMs)<n>Direct Preference Optimization (DPO) aims to learn directly from the corrected preferences provided by humans.<n>Existing preference pairs are often vision-agnostic and their inherently off-policy nature limits their effectiveness in guiding model learning.<n>We propose Perceptual Processing Direct Preference Optimization (P$2$-DPO), a novel training paradigm in which the model generates and learns from its own preference pairs.
  arXiv  Detail & Related papers  (2026-06-02T09:22:53Z)
• Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation [59.80828456543202]
  We propose Token-Level Visual-Sensitivity Steering (TLVS) for hallucination mitigation.<n>This mechanism requires only minimal training for calibration and can be applied across diverse vision-language models.<n>We evaluate TLVS on several benchmarks, including POPE, AMBER, CHAIR (COCO), MMHal, and HallusionBench, demonstrating consistent improvements over previous steering methods.
  arXiv  Detail & Related papers  (2026-06-02T08:23:28Z)
• DUEL: Adversarial Self-Play for Multimodal Reasoning [16.61891948648537]
  Reinforcement learning (RL) has emerged as an effective paradigm for improving the reasoning capability of vision-language models (VLMs)<n>We propose a self-evolving post-training framework, DUEL, where supervision emerges from adversarial interactions between two policies perturbed from the same pretrained VLM.<n>Experiments show that DUEL consistently improves visual reasoning and robust discrimination without additional human annotations, external reward models, or image editing tools.
  arXiv  Detail & Related papers  (2026-05-24T00:38:26Z)
• GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control [0.0]
  We introduce GIRL (Generative Imagination Reinforcement Learning), a latent world-model framework that addresses this failure mode with two key components.<n> GIRL reduces latent rollout drift by 38 to 61 percent across tasks relative to DreamerV3, improves return, and requires fewer environment interactions on long-horizon tasks.<n>A distilled-prior variant reduces overhead and improves computational efficiency relative to the full model.
  arXiv  Detail & Related papers  (2026-04-08T17:14:21Z)
• Same Answer, Different Representations: Hidden instability in VLMs [65.36933543377346]
  We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness.<n>We apply this framework to modern Vision Language Models (VLMs) across the SEEDBench, MMMU, and POPE datasets.
  arXiv  Detail & Related papers  (2026-02-06T12:24:26Z)
• ReViP: Reducing False Completion in Vision-Language-Action Models with Vision-Proprioception Rebalance [50.05984919728878]
  We present ReViP, a novel VLA framework with Vision-Proprioception Rebalance to enhance visual grounding and robustness under perturbations.<n>Specifically, we use an external VLM as a task-stage observer to extract real-time task-centric visual cues from visual observations.<n>To evaluate false completion, we propose the first False-Completion Benchmark Suite built on LIBERO with controlled settings such as Object-Drop.
  arXiv  Detail & Related papers  (2026-01-23T11:31:07Z)
• Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models [13.32858759983739]
  Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating text inconsistent with visual inputs.<n>Existing inference-time interventions to mitigate this issue present a challenging trade-off.<n>We present Residual-Update Directed DEcoding Regulation (RUDDER), a framework that steers LVLMs towards visually-grounded generation.
  arXiv  Detail & Related papers  (2025-11-13T13:29:38Z)
• Token-Level Inference-Time Alignment for Vision-Language Models [58.41370989069588]
  Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence.<n>We present TITA, a lightweight framework that freezes the base VLM and instead trains a reward model to approximate its distribution.<n>During inference, implicit preference signals are extracted as log-probability ratios between the reward model and the target VLM, yielding dense autoregressive feedback.
  arXiv  Detail & Related papers  (2025-10-20T09:58:03Z)
• VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning [62.09195763860549]
  Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models (LLMs) but struggles with exploration.<n>We introduce $textbfVOGUE (Visual Uncertainty Guided Exploration)$, a novel method that shifts exploration from the output (text) to the input (visual) space.<n>Our work shows that grounding exploration in the inherent uncertainty of visual inputs is an effective strategy for improving multimodal reasoning.
  arXiv  Detail & Related papers  (2025-10-01T20:32:08Z)
• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)
• Training Language Models to Self-Correct via Reinforcement Learning [98.35197671595343]
  Self-correction has been found to be largely ineffective in modern large language models (LLMs) We develop a multi-turn online reinforcement learning approach, SCoRe, that significantly improves an LLM's self-correction ability using entirely self-generated data. We find that SCoRe achieves state-of-the-art self-correction performance, improving the base models' self-correction by 15.6% and 9.1% respectively on MATH and HumanEval.
  arXiv  Detail & Related papers  (2024-09-19T17:16:21Z)

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.