Papers
arxiv:2410.16198

Improve Vision Language Model Chain-of-thought Reasoning

Published on Oct 21
· Submitted by ruohongz on Oct 23
#3 Paper of the day
Authors:
,
,
,
,
,
,

Abstract

Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes lack robust CoT reasoning data, relying on datasets dominated by short annotations with minimal rationales. In this work, we show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses. To address this, we propose a two-fold approach. First, we distill rationales from GPT-4o model to enrich the training data and fine-tune VLMs, boosting their CoT performance. Second, we apply reinforcement learning to further calibrate reasoning quality. Specifically, we construct positive (correct) and negative (incorrect) pairs of model-generated reasoning chains, by comparing their predictions with annotated short answers. Using this pairwise data, we apply the Direct Preference Optimization algorithm to refine the model's reasoning abilities. Our experiments demonstrate significant improvements in CoT reasoning on benchmark datasets and better generalization to direct answer prediction as well. This work emphasizes the importance of incorporating detailed rationales in training and leveraging reinforcement learning to strengthen the reasoning capabilities of VLMs.

Community

Paper author Paper submitter

Improve Visual Language Model Chain-of-thought Reasoning

paper link: https://arxiv.org/pdf/2410.16198

project page (to be released): https://github.com/RifleZhang/LLaVA-Reasoner-DPO

Content:

  1. We distill 193K CoT data
  2. Train with SFT
  3. DPO to futher improve performance

blog post: https://x.com/RuohongZhang/status/1848796433417220504

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2410.16198 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2410.16198 in a Space README.md to link it from this page.

Collections including this paper 5