Listener-Rewarded Thinking in VLMs for Image Preferences

[2506.22832] Listener-Rewarded Thinking in VLMs for Image Preferences Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computer Vision and Pattern Recognition arXiv:2506.22832 (cs) This paper has been withdrawn by Alexander Gambashidze [Submitted on 28 Jun 2025 ( v1 ), last revised 9 Apr 2026 (this version, v3)] Title: Listener-Rewarded Thinking in VLMs for Image Preferences Authors: Alexander Gambashidze , Li Pengyi , Matvey Skripkin , Andrey Galichin , Anton Gusarov , Konstantin Sobolev , Andrey Kuznetsov , Ivan Oseledets View a PDF of the paper titled Listener-Rewarded Thinking in VLMs for Image Preferences, by Alexander Gambashidze and 7 other authors No PDF available, click to view other formats Abstract: Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However, current reward models often fail to generalize, and supervised fine-tuning leads to memorization, demanding complex annotation pipelines. While reinforcement learning (RL), specifically Group Relative Policy Optimization (GRPO), improves generalization, we uncover a key failure mode: a significant drop in reasoning accuracy occurs when a model's reasoning trace contradicts that of an independent, frozen vision-language model ("listener") evaluating the same output. To address this, we introduce a listener-augmented GRPO framework. Here, the listener re-evaluates the reasoner's chain-of-thought to provide a dense, calibrated confidence score, shaping the RL reward signal. This encourages the reasoner not only to answer correctly, but to produce explanations that are persuasive to an independent model. Our listener-shaped reward scheme achieves best accuracy on the ImageReward benchmark (67.4%), significantly improves out-of-distribution (OOD) performance on a large-scale human preference dataset (1.2M votes, up to +6% over naive reasoner), and reduces reasoning contradictions compared to strong GRPO and SFT baselines. These results demonstrate that listener-based rewards provide a scalable, data-efficient path to aligning vision-language models with nuanced human preferences. We will release our reasoning model here: this https URL . Comments: part of a different work Subjects: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2506.22832 [cs.CV] (or arXiv:2506.22832v3 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2506.22832 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Alexander Gambashidze [ view email ] [v1] Sat, 28 Jun 2025 09:53:17 UTC (957 KB) [v2] Tue, 1 Jul 2025 13:53:50 UTC (957 KB) [v3] Thu, 9 Apr 2026 11:44:23 UTC (1 KB) (withdrawn) Full-text links: Access Paper: View a PDF of the paper titled Listener-Rewarded Thinking in VLMs for Image Preferences, by Alexander Gambashidze and 7 other authors Withdrawn No license for this version due to withdrawn Current browse context: cs.CV < prev | next > new | recent | 2025-06 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Behavioral signatures of post-decisional attention in preferential choice.#409118
• Where Do Embodied Decisions Come From? Rethinking Latent and Explicit Reasoning#1129412
• Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents#800059
• Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration#1078011
• A Survey on Efficient Vision-Language-Action Models#1129131