Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning

• URL: http://arxiv.org/abs/2606.01558v1
• Date: Mon, 01 Jun 2026 02:02:23 GMT
• Title: Attention-guided Fine-tuning of Multimodal Large Language Models Improves Chain-of-Thought Reasoning
• Abstract summary: Chain-of-Thought (CoT) prompting in Multimodal Large Language Models (MLLMs) remains uncertain.<n>We propose Attentive-CoT (Att-CoT), an attention-guided fine-tuning objective that encourages CoT trajectories to delay answer commitment.<n>Att-CoT can be plugged into any CoT-SFT training run without architectural changes.
• Score: 39.5490415037017
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The effectiveness of Chain-of-Thought (CoT) prompting in Multimodal Large Language Models (MLLMs) remains uncertain: across several visual reasoning benchmarks, CoT prompting often degrades performance compared to direct prompting. In this paper, we provide a systematic analysis of CoT behavior in three modern MLLM families across model scales on datasets requiring step-wise visual evidence. Our analysis identifies two recurring failure modes: premature answer commitment and limited direct visual-token access during rationale generation. We further find that standard CoT-style Supervised Fine-Tuning (CoT-SFT) can mitigate these issues only partially, while often increasing reliance on textual priors and reducing counterfactual visual dependence. Motivated by these findings, we propose Attentive-CoT (Att-CoT), an attention-guided fine-tuning objective that encourages CoT trajectories to delay answer commitment while maintaining sustained visual-token access. Att-CoT can be plugged into any CoT-SFT training run without architectural changes. Experiments on three visual reasoning benchmarks across six MLLMs show that Att-CoT enhances CoT performance over standard fine-tuning.

Related papers

• Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning [65.15766304205657]
  In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile.<n>Our analysis reveals that the fundamental limitation lies in an inductive gap, models often produce correct answers from flawed reasoning.<n>We introduce a framework that restructures multimodal ICL as a principled inductive-deductive process.
  arXiv  Detail & Related papers  (2026-05-04T09:18:19Z)
• Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought [15.598263332303612]
  Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse tasks.<n>This study dives into the foundations of these observations by addressing three critical questions.
  arXiv  Detail & Related papers  (2026-02-16T10:57:26Z)
• UniT: Unified Multimodal Chain-of-Thought Test-time Scaling [85.590774707406]
  Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs.<n>We introduce UniT, a framework for multimodal test-time scaling that enables a single unified model to reason, verify, and refine across multiple rounds.
  arXiv  Detail & Related papers  (2026-02-12T18:59:49Z)
• Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization [55.6995787502694]
  We study how different Chain-of-language (CoT) designs affect the acquisition of the generalizable visual reasoning ability.<n>We compare three representative CoT formats: Language CoT, Grounding CoT, and Visual CoT.<n>Our experiments reveal that visual and longer CoT mainly accelerate convergence but do not lift the final performance ceiling.
  arXiv  Detail & Related papers  (2025-11-27T16:19:34Z)
• Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision [30.155319213322013]
  Chain-of-Thought (CoT) reasoning has been widely adopted to enhance Large Language Models (LLMs)<n>We propose Uni-CoT, a Unified Chain-of-Thought framework that enables coherent and grounded multimodal reasoning.
  arXiv  Detail & Related papers  (2025-08-07T17:45:17Z)
• Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs [63.36637269634553]
  We introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.<n>We show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales.<n>Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models' ability to refine an initial reasoning chain.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)
• ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting [124.69672273754144]
  Chain-of-Thought (CoT) prompting can enhance the reasoning capabilities of large language models (LLMs) Existing CoT approaches usually focus on simpler reasoning tasks and thus result in low-quality and inconsistent CoT prompts. We introduce CoTGenius, a novel framework designed for the automatic generation of superior CoT prompts.
  arXiv  Detail & Related papers  (2024-03-21T11:34:26Z)
• Stress Testing Chain-of-Thought Prompting for Large Language Models [0.16317061277456998]
  This report examines the effectiveness of Chain-of-Thought (CoT) prompting in improving the multi-step reasoning abilities of large language models (LLMs) We analyze the impact of three types of CoT prompt perturbations, namely CoT order, CoT values, and CoT operators on the performance of GPT-3 on various tasks.
  arXiv  Detail & Related papers  (2023-09-28T17:21:33Z)

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.