{"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/concept-bottleneck-large-language-models","title":"Concept Bottleneck Large Language Models","arxiv_id":"2412.07992","date":"2024-12-11","proceeding":null,"authors":["Chung-En Sun","Tuomas Oikarinen","Berk Ustun","Tsui-Wei Weng"],"abstract":"We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs). Unlike traditional black-box LLMs that rely on post-hoc interpretation methods with limited neuron function insights, CB-LLM sets a new standard with its built-in interpretability, scalability, and ability to provide clear, accurate explanations. We investigate two essential tasks in the NLP domain: text classification and text generation. In text classification, CB-LLM narrows the performance gap with traditional black-box models and provides clear interpretability. In text generation, we show how interpretable neurons in CB-LLM can be used for concept detection and steering text generation. Our CB-LLMs enable greater interaction between humans and LLMs across a variety of tasks -- a feature notably absent in existing LLMs. Our code is available at https://github.com/Trustworthy-ML-Lab/CB-LLMs.","url_abs":"https://arxiv.org/abs/2412.07992v1","url_pdf":"https://arxiv.org/pdf/2412.07992v1.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":"concept-bottleneck-large-language-models","repo_url":"https://github.com/trustworthy-ml-lab/cb-llms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.07992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07992"}},"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":"deterministic:regex_extraction","url":"https://github.com/Trustworthy-ML-Lab/CB-LLMs","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/trustworthy-ml-lab/cb-llms","reach":null}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"b4d52b90da2c404d","entry":"build_loaders","repo":"Trustworthy-ML-Lab/CB-LLMs","repo_kind":"official","path":"classification/train_CBL.py","file_url":"https://github.com/Trustworthy-ML-Lab/CB-LLMs/blob/HEAD/classification/train_CBL.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4d52b90da2c404d"}},{"code_sha256_prefix":"5e4d23d654575355","entry":"build_loaders","repo":"Trustworthy-ML-Lab/CB-LLMs","repo_kind":"official","path":"generation/train_CBLLM.py","file_url":"https://github.com/Trustworthy-ML-Lab/CB-LLMs/blob/HEAD/generation/train_CBLLM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5e4d23d654575355"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}