mlsanityData to 14 Oct 2026

ReCo: Reminder Composition Mitigates Hallucinations in Vision-Language Models

arXiv 2506.22636 ↗First posted 27 Jun 2025cs.CVcited by 2

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

Abstract (arXiv)

Vision Language Models (VLMs) show impressive capabilities in integrating and reasoning with both visual and language data. But these models make mistakes. A common finding -- similar to LLMs -- is their tendency to hallucinate, i.e., generate plausible sounding text which is not grounded in the visual input, or at worst, is contradictory. A growing consensus attributes this behavior to an over-reliance on language -- especially as the generation progresses, the model suffers from a ``fading memory effect'' with respect to the provided visual input. We study mechanisms by which this behavior can be controlled. Specifically, using ideas from geometric algebra and relational compositions, we propose the addition of a small, trainable module (named ReCo) on top of any VLM -- no other modification is needed. We show that such a lightweight module is able to mitigate the fading memory effect on three of the most widely used VLMs (InstructBLIP, LlaVA, MiniGPT4), where we see performance improvements on multiple benchmarks. Additionally, we show that our module can be combined with many of the other approaches for reducing hallucination where we achieve improved results for each one.

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 12 of its 53 references that are in the map. First posted on arXiv 27 Jun 2025.

Builds on

12 of 53 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Reducing Hallucinations in Vision-Language Models via Latent Space Steering21 Oct
  2. 2024Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models28 May
  3. 2024A Survey on Hallucination in Large Vision-Language Models1 Feb
  4. 2023AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation13 Nov

Other references · 8

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  4. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  5. 2023Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understandingcited by 1,471
  6. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 625
  7. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 608
  8. 2020Pooling Methods in Deep Neural Networks, a Reviewcited by 52

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Concept Attractors in LLMs and their Applicationscited by 1
  2. 2026Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
  2. 2024Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
  3. 2025HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language Models
  4. 2025IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
  5. 2026Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
  6. 2025ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models
  7. 2023Evaluating Object Hallucination in Large Vision-Language Models
  8. 2025A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models