Papers › MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and...

MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration

6 Oct 2024arXiv:2410.04521archive 2025-07-28

Lai Wei, Wenkai Wang, Xiaoyu Shen, Yu Xie, Zhihao Fan, Xiaojin Zhang, Zhongyu Wei, Wei Chen

In recent advancements, multimodal large language models (MLLMs) have been fine-tuned on specific medical image datasets to address medical visual question answering (Med-VQA) tasks. However, this common approach of task-specific fine-tuning is costly and necessitates separate models for each downstream task, limiting the exploration of zero-shot capabilities. In this paper, we introduce MC-CoT, a modular cross-modal collaboration Chain-of-Thought (CoT) framework designed to enhance the zero-shot performance of MLLMs in Med-VQA by leveraging large language models (LLMs). MC-CoT improves reasoning and information extraction by integrating medical knowledge and task-specific guidance, where LLM provides various complex medical reasoning chains and MLLM provides various observations of medical images based on instructions of the LLM. Our experiments on datasets such as SLAKE, VQA-RAD, and PATH-VQA show that MC-CoT surpasses standalone MLLMs and various multimodality CoT frameworks in recall rate and accuracy. These findings highlight the importance of incorporating background information and detailed guidance in addressing complex zero-shot Med-VQA tasks.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2410.04521")

Code

Syntology Ran 15 of 15 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 15 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

thomaswei-cn/MC-CoT officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 15 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

15ran

Licence: 15 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from thomaswei-cn/MC-CoT. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

calculate thomaswei-cn/MC-CoT/evaluation/eval_recall.py official repository ran no licence file found · pointer only · 6b92bbd5846da32b · report
get_description_prompt thomaswei-cn/MC-CoT/method/MCCoT.py official repository ran fingerprinted no licence file found · pointer only · 90496e55127efecd · report
get_final_prompt thomaswei-cn/MC-CoT/method/IICoT.py official repository ran fingerprinted no licence file found · pointer only · 64df14f409178414 · report
get_llm_guide thomaswei-cn/MC-CoT/method/IICoT.py official repository ran fingerprinted no licence file found · pointer only · 5175e8cc0f49f1c7 · report
get_prompt thomaswei-cn/MC-CoT/method/VisualOnly.py official repository ran fingerprinted no licence file found · pointer only · 9c7f5d246b874c50 · report
get_prompt_1 thomaswei-cn/MC-CoT/method/DDCoT.py official repository ran fingerprinted no licence file found · pointer only · 000be3865cec37b5 · report
get_prompt_1 thomaswei-cn/MC-CoT/method/MMCoT.py official repository ran fingerprinted no licence file found · pointer only · 0af7dfa170b8908b · report
get_prompt_2 thomaswei-cn/MC-CoT/method/DDCoT.py official repository ran fingerprinted no licence file found · pointer only · 27f9b05e71702fe8 · report
get_prompt_2 thomaswei-cn/MC-CoT/method/MMCoT.py official repository ran fingerprinted no licence file found · pointer only · 73e8a59dd51c7a69 · report
get_qvix_prompt_stg1 thomaswei-cn/MC-CoT/method/Qvix.py official repository ran fingerprinted no licence file found · pointer only · 196a35d098174fae · report
get_qvix_prompt_stg2 thomaswei-cn/MC-CoT/method/Qvix.py official repository ran fingerprinted no licence file found · pointer only · 0257d60a33d66847 · report
get_rationale_with_guide thomaswei-cn/MC-CoT/method/IICoT.py official repository ran fingerprinted no licence file found · pointer only · cf691b4b36db3ef4 · report
get_total_score_with_len thomaswei-cn/MC-CoT/evaluation/eval_show.py official repository ran fingerprinted no licence file found · pointer only · 66b70633eccfaedb · report
is_module_required thomaswei-cn/MC-CoT/method/MCCoT.py official repository ran no licence file found · pointer only · 0fbe28a9f28a96ab · report
match_tasks thomaswei-cn/MC-CoT/method/MCCoT.py official repository ran fingerprinted no licence file found · pointer only · 504831ad705b7b9d · report

Tasks

Medical Visual Question AnsweringQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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