Papers › The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task
The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task
Yifan Wu, Pengchuan Zhang, Wenhan Xiong, Barlas Oguz, James C. Gee, Yixin Nie
The study explores the effectiveness of the Chain-of-Thought approach, known for its proficiency in language tasks by breaking them down into sub-tasks and intermediate steps, in improving vision-language tasks that demand sophisticated perception and reasoning. We present the "Description then Decision" strategy, which is inspired by how humans process signals. This strategy significantly improves probing task performance by 50%, establishing the groundwork for future research on reasoning paradigms in complex vision-language tasks.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Visual Reasoning | Winoground | GPT-4V (CoT, pick b/w two options) | Group Score | 58.75 | #2 of 114 | Archive leaderboard | report |
| Visual Reasoning | Winoground | GPT-4V (CoT, pick b/w two options) | Image Score | 68.75 | #2 of 114 | Archive leaderboard | report |
| Visual Reasoning | Winoground | GPT-4V (CoT, pick b/w two options) | Text Score | 75.25 | #2 of 114 | Archive leaderboard | report |
| Visual Reasoning | Winoground | GPT-4V (pick b/w two options) | Group Score | 39.25 | #3 of 114 | Archive leaderboard | report |
| Visual Reasoning | Winoground | GPT-4V (pick b/w two options) | Image Score | 46.25 | #3 of 114 | Archive leaderboard | report |
| Visual Reasoning | Winoground | GPT-4V (pick b/w two options) | Text Score | 69.25 | #3 of 114 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections