Papers › Multimodal Chain-of-Thought Reasoning in Language Models

Multimodal Chain-of-Thought Reasoning in Language Models

2 Feb 2023arXiv:2302.00923archive 2025-07-28

Zhuosheng Zhang, Aston Zhang, Mu Li, Hai Zhao, George Karypis, Alex Smola

Large language models (LLMs) have shown impressive performance on complex reasoning by leveraging chain-of-thought (CoT) prompting to generate intermediate reasoning chains as the rationale to infer the answer. However, existing CoT studies have primarily focused on the language modality. We propose Multimodal-CoT that incorporates language (text) and vision (images) modalities into a two-stage framework that separates rationale generation and answer inference. In this way, answer inference can leverage better generated rationales that are based on multimodal information. Experimental results on ScienceQA and A-OKVQA benchmark datasets show the effectiveness of our proposed approach. With Multimodal-CoT, our model under 1 billion parameters achieves state-of-the-art performance on the ScienceQA benchmark. Our analysis indicates that Multimodal-CoT offers the advantages of mitigating hallucination and enhancing convergence speed. Code is publicly available at https://github.com/amazon-science/mm-cot.

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="2302.00923")

Code

Syntology Ran 6 of 11 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 5 ran; community (archive-listed): 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

amazon-science/mm-cot officialmentioned in paperpytorchApache-2.0 report
chengtan9907/mc-cot mentioned on GitHubpytorch report
xqx12/daily-info mentioned on GitHubpytorch 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

11 samples harvested; 6 ran; 0 honoured the contract we drafted; 5 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.

4ran · our draft was wrong
2ran
5unverified

Licence: 1 of the 11 samples is 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

bleu_score amazon-science/mm-cot/evaluations.py official repository ran Apache-2.0 (permissive) · ab795c060d39c540 · report
caculate_bleu amazon-science/mm-cot/evaluations.py official repository ran Apache-2.0 (permissive) · 07349e17621c2b32 · report
get_choice_text amazon-science/mm-cot/utils_prompt.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 7a8dffc83d89cedd · report
get_context_text amazon-science/mm-cot/utils_prompt.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 85f084f6054a421e · report
get_question_text amazon-science/mm-cot/utils_prompt.py official repository ran · our draft was wrong Apache-2.0 (permissive) · c86a79e229253816 · report
extract_features amazon-science/mm-cot/extract_features.py official repository unverified Apache-2.0 (permissive) · 2ca16095ff60ecfc · report
get_acc_with_contion amazon-science/mm-cot/utils_evaluate.py official repository unverified Apache-2.0 (permissive) · cb95051c242a2b43 · report
interleave_blocks amazon-science/mm-cot/timm/models/byobnet.py official repository unverified Apache-2.0 (permissive) · 8c7fc90b1bea0d98 · report
load_data_img amazon-science/mm-cot/utils_data.py official repository unverified Apache-2.0 (permissive) · 583632f48d48f596 · report
load_data_std amazon-science/mm-cot/utils_data.py official repository unverified Apache-2.0 (permissive) · 68fb464d5cd3ca24 · report
tokenize chengtan9907/mc-cot/evaluation.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · e605721addd552ac · report

Tasks

HallucinationLanguage ModellingScience Question Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Science Question Answering ScienceQA Multimodal CoT Avg. Accuracy 91.68 #4 of 10 Archive leaderboard report
Science Question Answering ScienceQA Multimodal CoT Grades 1-6 92.44 #4 of 10 Archive leaderboard report
Science Question Answering ScienceQA Multimodal CoT Grades 7-12 90.31 #4 of 10 Archive leaderboard report
Science Question Answering ScienceQA Multimodal CoT Image Context 88.80 #4 of 10 Archive leaderboard report
Science Question Answering ScienceQA Multimodal CoT Language Science 90.82 #4 of 10 Archive leaderboard report
Science Question Answering ScienceQA Multimodal CoT Natural Science 95.91 #4 of 10 Archive leaderboard report
Science Question Answering ScienceQA Multimodal CoT No Context 92.89 #4 of 10 Archive leaderboard report
Science Question Answering ScienceQA Multimodal CoT Social Science 82.00 #4 of 10 Archive leaderboard report
Science Question Answering ScienceQA Multimodal CoT Text Context 95.26 #4 of 10 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