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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 15 ran (9 with no instrument failure; 6 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

thomaswei-cn/MC-CoT officialmentioned in paperpytorchSyntology: 15 samples, 15 ran (6 instrument-failed) · 0 unverified 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 (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
7ran

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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

thomaswei-cn/MC-CoT official repository 15 samples, 15 ran (6 instrument-failed) · 0 unverified
calculate in 13 papers evaluation/eval_recall.py ran no licence file found · pointer only · 6b92bbd5846da32b · report fixture: signature ref:str/0/str, pred:str/0/str, tokenizer:SimpleTokenizer/0/? · returned float · level recorded 2026-09-24
get_description_prompt method/MCCoT.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 90496e55127efecd · report fixture: signature question:str/0/str · returned str · level recorded 2026-09-24
get_final_prompt method/IICoT.py ran fingerprinted no licence file found · pointer only · 64df14f409178414 · report fixture: signature question:str/0/str, rationale:str/0/str · returned str · level recorded 2026-09-24
get_llm_guide method/IICoT.py ran fingerprinted no licence file found · pointer only · 5175e8cc0f49f1c7 · report fixture: signature question:str/0/str, domain:str/0/str · returned str · level recorded 2026-09-24
get_prompt in 99 papers method/VisualOnly.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9c7f5d246b874c50 · report fixture: signature question:str/0/str · returned str · level recorded 2026-09-24
get_prompt_1 method/DDCoT.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 000be3865cec37b5 · report fixture: signature question:str/0/str · returned tuple · level recorded 2026-09-24
get_prompt_1 method/MMCoT.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 0af7dfa170b8908b · report fixture: signature question:str/0/str · returned str · level recorded 2026-09-24
get_prompt_2 method/DDCoT.py ran fingerprinted no licence file found · pointer only · 27f9b05e71702fe8 · report fixture: signature question:str/0/str, preliminary_knowledge:str/0/str · returned tuple · level recorded 2026-09-24
get_prompt_2 method/MMCoT.py ran fingerprinted no licence file found · pointer only · 73e8a59dd51c7a69 · report fixture: signature question:str/0/str, rationale:str/0/str · returned str · level recorded 2026-09-24
get_qvix_prompt_stg1 method/Qvix.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 196a35d098174fae · report fixture: signature question:str/0/str · returned str · level recorded 2026-09-24
get_qvix_prompt_stg2 method/Qvix.py ran fingerprinted no licence file found · pointer only · 0257d60a33d66847 · report fixture: signature question:str/0/str, preques:str/0/str · returned str · level recorded 2026-09-24
get_rationale_with_guide method/IICoT.py ran fingerprinted no licence file found · pointer only · cf691b4b36db3ef4 · report fixture: signature question:str/0/str, llm_guide:str/0/str · returned str · level recorded 2026-09-24
get_total_score_with_len evaluation/eval_show.py ran · honoured contract fingerprinted no licence file found · pointer only · 66b70633eccfaedb · report fixture: signature json_filename:str/0/str · returned tuple · level recorded 2026-09-24
is_module_required method/MCCoT.py ran · violated contract no licence file found · pointer only · 0fbe28a9f28a96ab · report fixture: signature text:str/0/str · returned bool · level recorded 2026-09-24
match_tasks method/MCCoT.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 504831ad705b7b9d · report fixture: signature decision:str/0/str · returned dict · level recorded 2026-09-24

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