{"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/finding-and-editing-multi-modal-neurons-in","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","arxiv_id":"2311.07470","date":"2023-11-13","proceeding":null,"authors":["Haowen Pan","Yixin Cao","Xiaozhi Wang","Xun Yang","Meng Wang"],"abstract":"Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia and industry. In this paper, we propose a novel method to identify key neurons for interpretability -- how multi-modal LLMs bridge visual and textual concepts for captioning. Our method improves conventional works upon efficiency and applied range by removing needs of costly gradient computation. Based on those identified neurons, we further design a multi-modal knowledge editing method, beneficial to mitigate sensitive words or hallucination. For rationale of our design, we provide theoretical assumption. For empirical evaluation, we have conducted extensive quantitative and qualitative experiments. The results not only validate the effectiveness of our methods, but also offer insightful findings that highlight three key properties of multi-modal neurons: sensitivity, specificity and causal-effect, to shed light for future research.","url_abs":"https://arxiv.org/abs/2311.07470v2","url_pdf":"https://arxiv.org/pdf/2311.07470v2.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":"finding-and-editing-multi-modal-neurons-in","repo_url":"https://github.com/opanhw/MM_Neurons","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"specificity","task_name":"Specificity"},{"task_slug":"knowledge-editing","task_name":"knowledge editing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.07470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07470"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/opanhw/MM_Neurons","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"ca16d1dfb73d4168","entry":"bilinear_interpolation","repo":"opanhw/MM_Neurons","repo_kind":"official","path":"src/trainer.py","file_url":"https://github.com/opanhw/MM_Neurons/blob/HEAD/src/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca16d1dfb73d4168"}},{"code_sha256_prefix":"5471d8474aec3d71","entry":"load_sbu","repo":"opanhw/MM_Neurons","repo_kind":"official","path":"src/load_datasets.py","file_url":"https://github.com/opanhw/MM_Neurons/blob/HEAD/src/load_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5471d8474aec3d71"}},{"code_sha256_prefix":"4552e857b0cf7ef7","entry":"load_image","repo":"opanhw/MM_Neurons","repo_kind":"official","path":"src/load_datasets.py","file_url":"https://github.com/opanhw/MM_Neurons/blob/HEAD/src/load_datasets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4552e857b0cf7ef7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}