{"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/if-concept-bottlenecks-are-the-question-are","title":"If Concept Bottlenecks are the Question, are Foundation Models the Answer?","arxiv_id":"2504.19774","date":"2025-04-28","proceeding":null,"authors":["Nicola Debole","Pietro Barbiero","Francesco Giannini","Andrea Passeggini","Stefano Teso","Emanuele Marconato"],"abstract":"Concept Bottleneck Models (CBMs) are neural networks designed to conjoin high performance with ante-hoc interpretability. CBMs work by first mapping inputs (e.g., images) to high-level concepts (e.g., visible objects and their properties) and then use these to solve a downstream task (e.g., tagging or scoring an image) in an interpretable manner. Their performance and interpretability, however, hinge on the quality of the concepts they learn. The go-to strategy for ensuring good quality concepts is to leverage expert annotations, which are expensive to collect and seldom available in applications. Researchers have recently addressed this issue by introducing \"VLM-CBM\" architectures that replace manual annotations with weak supervision from foundation models. It is however unclear what is the impact of doing so on the quality of the learned concepts. To answer this question, we put state-of-the-art VLM-CBMs to the test, analyzing their learned concepts empirically using a selection of significant metrics. Our results show that, depending on the task, VLM supervision can sensibly differ from expert annotations, and that concept accuracy and quality are not strongly correlated. Our code is available at https://github.com/debryu/CQA.","url_abs":"https://arxiv.org/abs/2504.19774v1","url_pdf":"https://arxiv.org/pdf/2504.19774v1.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":"if-concept-bottlenecks-are-the-question-are","repo_url":"https://github.com/debryu/CQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.19774","atlas_url":"https://app.syntology.ai/?focus=2504.19774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.19774"}},"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/debryu/CQA","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"3c99e15cd6c954b5","entry":"folder_naming_convention","repo":"debryu/CQA","repo_kind":"official","path":"CQA/config.py","file_url":"https://github.com/debryu/CQA/blob/HEAD/CQA/config.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":"3c99e15cd6c954b5"}},{"code_sha256_prefix":"f96d1d83d32d1b0d","entry":"get_backbone_function","repo":"debryu/CQA","repo_kind":"official","path":"CQA/models/argo.py","file_url":"https://github.com/debryu/CQA/blob/HEAD/CQA/models/argo.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":"f96d1d83d32d1b0d"}},{"code_sha256_prefix":"94d887d05ea17e39","entry":"open_CQA","repo":"debryu/CQA","repo_kind":"official","path":"CQA/core/concept_quality.py","file_url":"https://github.com/debryu/CQA/blob/HEAD/CQA/core/concept_quality.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"94d887d05ea17e39"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}