{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multimodal-chain-of-thought-reasoning-in","title":"Multimodal Chain-of-Thought Reasoning in Language Models","arxiv_id":"2302.00923","date":"2023-02-02","proceeding":null,"authors":["Zhuosheng Zhang","Aston Zhang","Mu Li","Hai Zhao","George Karypis","Alex Smola"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2302.00923v5","url_pdf":"https://arxiv.org/pdf/2302.00923v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multimodal-chain-of-thought-reasoning-in","repo_url":"https://github.com/amazon-science/mm-cot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"multimodal-chain-of-thought-reasoning-in","repo_url":"https://github.com/chengtan9907/mc-cot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multimodal-chain-of-thought-reasoning-in","repo_url":"https://github.com/xqx12/daily-info","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"science-question-answering","task_name":"Science Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/science-question-answering-on-scienceqa","task":"Science Question Answering","dataset":"ScienceQA","model":"Multimodal CoT","rank_in_archive_order":4,"of":10,"metrics":{"Avg. Accuracy":"91.68","Grades 1-6":"92.44","Grades 7-12":"90.31","Image Context":"88.80","Language Science":"90.82","Natural Science":"95.91","No Context":"92.89","Social Science":"82.00","Text Context":"95.26"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.00923","atlas_url":"https://app.syntology.ai/?focus=2302.00923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00923"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chengtan9907/mc-cot","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/amazon-science/mm-cot","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xqx12/daily-info","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_draft_wrong":4,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"ab795c060d39c540","entry":"bleu_score","repo":"amazon-science/mm-cot","repo_kind":"official","path":"evaluations.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/evaluations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ab795c060d39c540"}},{"code_sha256_prefix":"07349e17621c2b32","entry":"caculate_bleu","repo":"amazon-science/mm-cot","repo_kind":"official","path":"evaluations.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/evaluations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"07349e17621c2b32"}},{"code_sha256_prefix":"cb95051c242a2b43","entry":"get_acc_with_contion","repo":"amazon-science/mm-cot","repo_kind":"official","path":"utils_evaluate.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/utils_evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb95051c242a2b43"}},{"code_sha256_prefix":"7a8dffc83d89cedd","entry":"get_choice_text","repo":"amazon-science/mm-cot","repo_kind":"official","path":"utils_prompt.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/utils_prompt.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a8dffc83d89cedd"}},{"code_sha256_prefix":"85f084f6054a421e","entry":"get_context_text","repo":"amazon-science/mm-cot","repo_kind":"official","path":"utils_prompt.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/utils_prompt.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"85f084f6054a421e"}},{"code_sha256_prefix":"c86a79e229253816","entry":"get_question_text","repo":"amazon-science/mm-cot","repo_kind":"official","path":"utils_prompt.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/utils_prompt.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c86a79e229253816"}},{"code_sha256_prefix":"68fb464d5cd3ca24","entry":"load_data_std","repo":"amazon-science/mm-cot","repo_kind":"official","path":"utils_data.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/utils_data.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"68fb464d5cd3ca24"}},{"code_sha256_prefix":"e605721addd552ac","entry":"tokenize","repo":"chengtan9907/mc-cot","repo_kind":"listed","path":"evaluation.py","file_url":"https://github.com/chengtan9907/mc-cot/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e605721addd552ac"}},{"code_sha256_prefix":"2ca16095ff60ecfc","entry":"extract_features","repo":"amazon-science/mm-cot","repo_kind":"official","path":"extract_features.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/extract_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ca16095ff60ecfc"}},{"code_sha256_prefix":"8c7fc90b1bea0d98","entry":"interleave_blocks","repo":"amazon-science/mm-cot","repo_kind":"official","path":"timm/models/byobnet.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/timm/models/byobnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c7fc90b1bea0d98"}},{"code_sha256_prefix":"583632f48d48f596","entry":"load_data_img","repo":"amazon-science/mm-cot","repo_kind":"official","path":"utils_data.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/utils_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"583632f48d48f596"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}