mlsanityData to 14 Oct 2026

Preemptive Hallucination Reduction: An Input-Level Approach for Multimodal Language Model

arXiv 2505.24007 ↗First posted 29 May 2025cs.CVcited by 2

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

Abstract (arXiv)

Visual hallucinations in Large Language Models (LLMs), where the model generates responses that are inconsistent with the visual input, pose a significant challenge to their reliability, particularly in contexts where precise and trustworthy outputs are critical. Current research largely emphasizes post-hoc correction or model-specific fine-tuning strategies, with limited exploration of preprocessing techniques to address hallucination issues at the input stage. This study presents a novel ensemble-based preprocessing framework that adaptively selects the most appropriate filtering approach -- noise reduced (NR), edge enhanced (EE), or unaltered input (org) based on the type of question posed, resulting into reduced hallucination without requiring any modifications to the underlying model architecture or training pipeline. Evaluated on the `HaloQuest' dataset -- a benchmark designed to test multimodal reasoning on visually complex inputs, our method achieves a 44.3% reduction in hallucination rates, as measured by Natural Language Inference (NLI) scores using SelfCheckGPT. This demonstrates that intelligent input conditioning alone can significantly enhance factual grounding in LLM responses. The findings highlight the importance of adaptive preprocessing techniques in mitigating hallucinations, paving the way for more reliable multimodal systems capable of addressing real-world challenges.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 32 of its 47 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

32 of 47 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention13 Mar
  2. 2024Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization15 Nov
  3. 2024HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning22 Jul
  4. 2024AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models16 Jun
  5. 2024Detecting and Evaluating Medical Hallucinations in Large Vision Language Models14 Jun
  6. 2024CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models4 Jun
  7. 2024Hallucination of Multimodal Large Language Models: A Survey29 Apr
  8. 2024Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination21 Mar
  9. 2024Visual Hallucinations of Multi-modal Large Language Models22 Feb
  10. 2023Hallucination Augmented Contrastive Learning for Multimodal Large Language Model12 Dec
  11. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization28 Nov
  12. 2023HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data22 Nov
5 more
  1. 2023Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision13 Nov
  2. 2023Woodpecker: Hallucination Correction for Multimodal Large Language Models24 Oct
  3. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Models1 Oct
  4. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning26 Jun
  5. 2023Evaluating Object Hallucination in Large Vision-Language Models17 May

Other references · 15

  1. 2023Visual Instruction Tuningcited by 7,869
  2. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  3. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  4. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  6. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  7. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,040
  8. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  9. 2023Vision-Language Models for Vision Tasks: A Surveycited by 839
  10. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  11. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 712
  12. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 332
3 more
  1. 2023Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Frameworkcited by 11
  2. 2024Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolutioncited by 11
  3. 2025Performance Evaluation of Large Language Models in Bangla Consumer Health Query Summarizationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Few-Shot Learning Pipeline for Monkeypox Skin Disease Classification Using CNN Feature Extractorscited by 0
  2. 2026Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Grounded Post-Training with Hard Examples for Reducing Hallucination in Multimodal Large Language Models
  2. 2024Combating Multimodal LLM Hallucination via Bottom-Up Holistic Reasoning
  3. 2024Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations
  4. 2025Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding
  5. 2025Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
  6. 2025Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection
  7. 2024Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
  8. 2026Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization