{"ID":2829498,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.12218","arxiv_id":"2512.12218","title":"Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking","abstract":"Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful intermediate steps, or reason faithfully yet fail on the final prediction. Standard evaluations that only measure final-answer accuracy cannot distinguish these behaviors. We introduce the visual faithfulness of reasoning chains as a distinct evaluation dimension, focusing on whether the perception steps of a reasoning chain are grounded in the image. We propose a training- and reference-free framework that decomposes chains into perception versus reasoning steps and uses off-the-shelf VLM judges for step-level faithfulness, additionally verifying this approach through a human meta-evaluation. Building on this metric, we present a lightweight self-reflection procedure that detects and locally regenerates unfaithful perception steps without any training. Across multiple reasoning-trained VLMs and perception-heavy benchmarks, our method reduces Unfaithful Perception Rate while preserving final-answer accuracy, improving the reliability of multimodal reasoning.","short_abstract":"Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful intermediate steps, or reason faithfully yet fail on the final prediction. Standard evalua...","url_abs":"https://arxiv.org/abs/2512.12218","url_pdf":"https://arxiv.org/pdf/2512.12218v2","authors":"[\"Rheeya Uppaal\",\"Phu Mon Htut\",\"Min Bai\",\"Nikolaos Pappas\",\"Zheng Qi\",\"Sandesh Swamy\"]","published":"2025-12-13T07:04:42Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.CL\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}