mlsanityData to 7 Oct 2026

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models

arXiv 2602.11824 ↗First posted 12 Feb 2026cs.AI cs.LGcited by 3

On the map: Multimodal LLMs / vision-language models → Hallucination mitigation in LVLMs

Abstract (arXiv)

Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper network layers. To address this, we propose REVIS, a training-free framework designed to explicitly re-activate this suppressed visual information. Rooted in latent space geometry, REVIS extracts the pure visual information vector via orthogonal projection and employs a calibrated strategy to perform sparse intervention only at the precise depth where suppression occurs. This surgical approach effectively restores visual information with minimal computational cost. Empirical evaluations on standard benchmarks demonstrate that REVIS reduces object hallucination rates by approximately 19% compared to state-of-the-art baselines, while preserving general reasoning capabilities.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 28 of its 28 references that are in the map. First posted on arXiv 12 Feb 2026.

Builds on

28 of 28 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key16 Jan
  2. 2024Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection18 Dec
  3. 2024Reducing Hallucinations in Vision-Language Models via Latent Space Steering21 Oct
  4. 2024Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs31 Jul
  5. 2024Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention18 Jun
  6. 2024Multi-Modal Hallucination Control by Visual Information Grounding20 Mar
  7. 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
  8. 2023Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov
  9. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization28 Nov
  10. 2023Evaluating Object Hallucination in Large Vision-Language Models17 May

Other references · 18

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2023Visual Instruction Tuningcited by 7,792
  4. 2025Qwen2.5-VL Technical Reportcited by 5,418
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  6. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  7. 2025Qwen3-VL Technical Reportcited by 2,534
  8. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  9. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  10. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
  11. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,239
  12. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,221
6 more
  1. 2023A Survey on Multimodal Large Language Modelscited by 898
  2. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  3. 2018Object Hallucination in Image Captioningcited by 661
  4. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 494
  5. 2025Why Language Models Hallucinatecited by 205
  6. 2026Emergent Introspective Awareness in Large Language Modelscited by 73

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Evidence-RL: Towards Evidence-intensive Visual Reasoningcited by 3
  2. 2026Prior Directions: Why GUI Grounding Gets Locked in the Pastcited by 0
  3. 2026Semantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
  2. 2026Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
  3. 2025Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations
  4. 2025SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination
  5. 2026NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors
  6. 2025Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow
  7. 2025VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering
  8. 2026Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering