Pith. sign in

REVIEW 5 cited by

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.14895 v1 pith:2UJEODLO submitted 2025-03-19 cs.CV cs.AIcs.CL

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations

classification cs.CV cs.AIcs.CL
keywords hallucinationsfeaturesmethodmllmsobjectmitigatingmodelmulti-frequency
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Recently, multimodal large language models (MLLMs) have demonstrated remarkable performance in visual-language tasks. However, the authenticity of the responses generated by MLLMs is often compromised by object hallucinations. We identify that a key cause of these hallucinations is the model's over-susceptibility to specific image frequency features in detecting objects. In this paper, we introduce Multi-Frequency Perturbations (MFP), a simple, cost-effective, and pluggable method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference, thereby mitigating hallucinations. Experimental results demonstrate that our method significantly mitigates object hallucinations across various model architectures. Furthermore, as a training-time method, MFP can be combined with inference-time methods to achieve state-of-the-art performance on the CHAIR benchmark.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models

    cs.CV 2026-04 unverdicted novelty 7.0

    DO-Bench is a controlled benchmark that attributes VLM object hallucination errors to textual prior pressure, perceptual limits, or their interaction via two diagnostic dimensions and metrics.

  2. Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation

    cs.CL 2026-04 unverdicted novelty 7.0

    DeP mitigates MLLM hallucinations by dynamically perturbing text prompts to identify and reinforce stable visual evidence regions while counteracting language prior biases using attention variance and logit statistics.

  3. Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation

    cs.CV 2026-06 unverdicted novelty 6.0

    OPPO is an evidence-aware preference optimization objective that contrasts faithful responses under varying visual evidence strengths to reduce hallucinations in MLLMs.

  4. Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward

    cs.CV 2026-04 unverdicted novelty 6.0

    Saliency-R1 uses a novel saliency map technique and GRPO with human bounding-box overlap as reward to improve VLM reasoning faithfulness and interpretability.

  5. Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation

    cs.CV 2026-06 unverdicted novelty 5.0

    OPPO is an evidence-aware preference optimization that contrasts faithful responses under varying visual evidence strengths to reduce hallucinations in MLLMs.