paper-with-me

Papers

Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine

2026-03-02 · Yuan Wu, Zongxian Yang, Jiayu Qian, Songpan Gao, Guanxing Chen, Qiankun Li, Yu-An Huang, Zhi-An Huang arxiv

Large vision-language models (VLMs) often benefit from chain-of-thought (CoT) prompting in general domains, yet its efficacy in medical vision-language tasks remains underexplored. We report a counter-intuitive trend: on medical visual question answering, CoT frequently underperforms direct answering (DirA) across general-purpose and medical-specific models. We attribute this to a \emph{medical perception bottleneck}: subtle, domain-specific cues can weaken visual grounding, and CoT may compound early perceptual uncertainty rather than correct it. To probe this hypothesis, we introduce two training-free, inference-time grounding interventions: (i) \emph{perception anchoring} via region-of-interest cues and (ii) \emph{description grounding} via high-quality textual guidance. Across multiple benchmarks and model families, these interventions improve accuracy, mitigate CoT degradation, and in several settings reverse the CoT--DirA inversion. Our findings suggest that reliable clinical VLMs require robust visual grounding and cross-modal alignment, beyond extending text-driven reasoning chains. Code is available \href{https://github.com/TianYin123/Better_Eyes_Better_Thoughts}{here}.

📄 PDF Abstract BibTeX arXiv:2603.06665

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question AnsweringVisual Grounding

Similar Papers 제목 키워드 기반

ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning

2025-10-30 · Jiawei Gu, Yunzhuo Hao, Huichen Will Wang, Linjie Li 외 arxiv

Multimodal reasoning requires iterative coordination between language and vision, yet it remains unclear what constitutes a meaningful interleaved chain of thought. We posit that text and image thoughts should function a…

Multimodal Reasoning

Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs

2026-02-18 · Felix Fricke, Simon Malberg, Georg Groh arxiv

Prompting schemes such as Chain of Thought, Tree of Thoughts, and Graph of Thoughts can significantly enhance the reasoning capabilities of large language models. However, most existing schemes require users to define st…

Caterpillar of Thoughts: The Optimal Test-Time Algorithm for Large Language Models

2026-03-24 · Amir Azarmehr, Soheil Behnezhad, Alma Ghafari arxiv

Large language models (LLMs) can often produce substantially better outputs when allowed to use additional test-time computation, such as sampling, chain of thought, backtracking, or revising partial solutions. Despite t…

Tree of Problems: Improving structured problem solving with compositionality

2024-10-09 · Armel Zebaze, Benoît Sagot, Rachel Bawden

Large Language Models (LLMs) have demonstrated remarkable performance across multiple tasks through in-context learning. For complex reasoning tasks that require step-by-step thinking, Chain-of-Thought (CoT) prompting ha…

In-Context Learning

Chain-of-Anomaly Thoughts with Large Vision-Language Models

2025-12-23 · Pedro Domingos, João Pereira, Vasco Lopes, João Neves 외 arxiv

Automated video surveillance with Large Vision-Language Models is limited by their inherent bias towards normality, often failing to detect crimes. While Chain-of-Thought reasoning strategies show significant potential f…

Anomaly ClassificationAnomaly Detection