Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces

• URL: http://arxiv.org/abs/2509.26594v1
• Date: Tue, 30 Sep 2025 17:46:46 GMT
• Title: Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces
• Authors: John Gkountouras, Ivan Titov,
• Abstract summary: We propose Adaptive-Clarification Reinforcement Learning (AC-RL), which teaches vision models what information reasoners need through interaction.<n>AC-RL improves average accuracy by 4.4 points over pretrained baselines across seven visual mathematical reasoning benchmarks.
• Score: 14.074625212174494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent text-only models demonstrate remarkable mathematical reasoning capabilities. Extending these to visual domains requires vision-language models to translate images into text descriptions. However, current models, trained to produce captions for human readers, often omit the precise details that reasoning systems require. This creates an interface mismatch: reasoners often fail not due to reasoning limitations but because they lack access to critical visual information. We propose Adaptive-Clarification Reinforcement Learning (AC-RL), which teaches vision models what information reasoners need through interaction. Our key insight is that clarification requests during training reveal information gaps; by penalizing success that requires clarification, we create pressure for comprehensive initial captions that enable the reasoner to solve the problem in a single pass. AC-RL improves average accuracy by 4.4 points over pretrained baselines across seven visual mathematical reasoning benchmarks, and analysis shows it would cut clarification requests by up to 39% if those were allowed. By treating clarification as a form of implicit supervision, AC-RL demonstrates that vision-language interfaces can be effectively learned through interaction alone, without requiring explicit annotations.

Related papers

• Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning [79.95774256444956]
  The lack of reasoning capabilities in Vision-Language Models has remained at the forefront of research discourse.<n>We investigate the data underlying the popular VLMs OpenCLIP, LLaVA-1.5 and Molmo through the lens of theories from pragmatics.
  arXiv  Detail & Related papers  (2026-02-26T18:54:06Z)
• Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy [75.66913260900726]
  Reinforcement Learning with Verifiable Rewards has significantly advanced reasoning capabilities in Large Language Models.<n>Existing paradigms, driven by text-centric outcome rewards, encourage models to bypass visual perception.<n>We propose textbfThinking with Deltas, a framework driven by a textbfDifferential Visual Reasoning Policy.
  arXiv  Detail & Related papers  (2026-01-11T08:25:34Z)
• Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information [13.94596271015724]
  Long reasoning dilutes visual tokens, causing visual information to receive less attention and may trigger hallucinations.<n>We introduce Qwen-LookAgain (Qwen-LA), a novel vision-text reflection process that guides the model to re-attention visual information during reasoning.
  arXiv  Detail & Related papers  (2025-05-29T15:34:15Z)
• Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning [41.59815187158526]
  We train visual language models (VLMs) to perform reasoning on image data through reinforcement learning and visual question-answer pairs.<n>Our model, named Visionary-R1, outperforms strong multimodal models on multiple visual reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-05-20T17:58:35Z)
• Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios [69.00444996464662]
  We propose RIV-CoT, a Retrieval-Based Interleaved Visual Chain-of-Thought method that enables vision-language models to reason using visual crops corresponding to relevant entities.<n>Our experiments demonstrate that RIV-CoT improves answer accuracy by 3.1% and reasoning accuracy by 4.6% over vanilla CoT prompting.
  arXiv  Detail & Related papers  (2025-01-08T18:31:16Z)
• FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability [10.184567639685321]
  We introduce FiVL, a novel method for constructing datasets designed to train LVLMs for enhanced visual grounding.<n>We present benchmarks to assess the model's ability to use image as substantive evidence.<n>We identify attention heads with the strongest vision-language alignment, enabling explainability on visual-driven hallucinations.
  arXiv  Detail & Related papers  (2024-12-19T09:24:10Z)
• Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models [59.05769810380928]
  Rephrase, Augment and Reason (RepARe) is a gradient-free framework that extracts salient details about the image using the underlying vision-language model. We show that RepARe can result in a 3.85% (absolute) increase in zero-shot accuracy on VQAv2, 6.41%, and 7.94% points increase on A-OKVQA, and VizWiz respectively.
  arXiv  Detail & Related papers  (2023-10-09T16:57:57Z)
• Interpretable Visual Question Answering via Reasoning Supervision [4.76359068115052]
  Transformer-based architectures have recently demonstrated remarkable performance in the Visual Question Answering (VQA) task. We propose a novel architecture for visual question answering that leverages common sense reasoning as a supervisory signal. We demonstrate both quantitatively and qualitatively that the proposed approach can boost the model's visual perception capability and lead to performance increase.
  arXiv  Detail & Related papers  (2023-09-07T14:12:31Z)
• See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning [60.43585179885355]
  We propose a novel framework named Interactive Prompting Visual Reasoner (IPVR) for few-shot knowledge-based visual reasoning. IPVR contains three stages, see, think and confirm. We conduct experiments on a range of knowledge-based visual reasoning datasets.
  arXiv  Detail & Related papers  (2023-01-12T18:59:50Z)
• SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification [84.05253637260743]
  We propose a new framework, named Semantic-guided Visual Adapting (SgVA), to extend vision-language pre-trained models. SgVA produces discriminative task-specific visual features by comprehensively using a vision-specific contrastive loss, a cross-modal contrastive loss, and an implicit knowledge distillation. State-of-the-art results on 13 datasets demonstrate that the adapted visual features can well complement the cross-modal features to improve few-shot image classification.
  arXiv  Detail & Related papers  (2022-11-28T14:58:15Z)
• Learning to Decompose Visual Features with Latent Textual Prompts [140.2117637223449]
  We propose Decomposed Feature Prompting (DeFo) to improve vision-language models. Our empirical study shows DeFo's significance in improving the vision-language models.
  arXiv  Detail & Related papers  (2022-10-09T15:40:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.