Skip to content

Evidence-RL: Towards Evidence-intensive Visual Reasoning

Aug 2026 · 3 citations · 47 references
Computer Science

TL;DR

This work proposes Counterfactual Evidence Disentanglement (CED), a training-time evidence audit for VLM grounding, which outperforms prior RL-based post-training methods, with targeted analyses verifying its object-centric signal.

Abstract

Vision-Language Models (VLMs) should answer from concrete image evidence rather than language priors, dataset shortcuts, or irrelevant visual context. Existing perception-aware post-training methods encourage image use through global perturbations or attention proxies, but they do not test whether a sampled answer causally depends on the local evidence that supports it. We propose Counterfactual Evidence Disentanglement (CED), a training-time evidence audit for VLM grounding. For each response, CED neutralizes an object-centric Evidence Region and compares the resulting support drop against matched non-evidence Regions. We combine this signal with answer correctness inside GRPO, rewarding correct answers that rely on the evidence path rather than shortcut or nuisance paths. CED uses weak object-level proposals, requires no question-specific evidence annotations, and adds no inference-time overhead. Across nine public benchmarks and four backbones, CED outperforms prior RL-based post-training methods, with targeted analyses verifying its object-centric signal.

View source

Similar papers

Preprint Sep 2026

Look Where It Counts: A Free, Label-Free Visual Evidence Signal for Fine-Grained Vision-Language Reasoning

The contrastive evidence gap is formalized, the per-token log-likelihood ratio that a model assigns to its own output when conditioned on a question-relevant region versus an irrelevant one, and it is shown that the gap is complementary to the model's own confidence.

Santiram Tiwari, N. Naik, Devbrat Pandey et al. · 0 citations
Preprint Sep 2026

Don't Just Look, Intervene: Perturbation Based Region Labeling for VQA Images

Across competing automatic region-labeling mechanisms, CSGR annotations provide the most consistent gains over Cross Entropy-only finetuning in both in-domain and out-of-domain evaluations, indicating that the proposed labeling scheme captures useful region-level information.

Marko Jojic, Zhao-Nan Li, Ben Zhou · 0 citations

From Perception to Integration: Revisiting the Internal Dynamics of Reasoning in Vision-Language Models

A small detector is trained to predict the internal development of answer readiness and stop reasoning at that point, connecting the internal development of answer readiness to a practical rule for allocating reasoning computation.

Rong-Yu Xu, Prayag Tiwari, Shao-Lei Zhang · 0 citations
Preprint Aug 2026

Answer-Level Trust Selection for Physical Vision-Language Reasoning

The results show that intervention-based diagnostics help identify stable-but-wrong and prior-tracking predictions that repeated agreement alone may miss, and a post-hoc, model-agnostic framework for accepting or rejecting individual VLM predictions is proposed, called Answer-Level Trust Selection (ATS).

Rongyu Yu, Ke Niu, Feng-Xiang He · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.