{"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/scaled-up-discovery-of-latent-concepts-in","title":"Scaling up Discovery of Latent Concepts in Deep NLP Models","arxiv_id":"2308.10263","date":"2023-08-20","proceeding":null,"authors":["Majd Hawasly","Fahim Dalvi","Nadir Durrani"],"abstract":"Despite the revolution caused by deep NLP models, they remain black boxes, necessitating research to understand their decision-making processes. A recent work by Dalvi et al. (2022) carried out representation analysis through the lens of clustering latent spaces within pre-trained models (PLMs), but that approach is limited to small scale due to the high cost of running Agglomerative hierarchical clustering. This paper studies clustering algorithms in order to scale the discovery of encoded concepts in PLM representations to larger datasets and models. We propose metrics for assessing the quality of discovered latent concepts and use them to compare the studied clustering algorithms. We found that K-Means-based concept discovery significantly enhances efficiency while maintaining the quality of the obtained concepts. Furthermore, we demonstrate the practicality of this newfound efficiency by scaling latent concept discovery to LLMs and phrasal concepts.","url_abs":"https://arxiv.org/abs/2308.10263v2","url_pdf":"https://arxiv.org/pdf/2308.10263v2.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":"scaled-up-discovery-of-latent-concepts-in","repo_url":"https://github.com/qcri/latent_concept_analysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.10263","atlas_url":"https://app.syntology.ai/?focus=2308.10263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.10263"}},"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/qcri/latent_concept_analysis","reach":null}],"summary":{"ran_draft_wrong":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":"c6386836e08b5639","entry":"filter_label_map","repo":"qcri/latent_concept_analysis","repo_kind":"official","path":"alignment.py","file_url":"https://github.com/qcri/latent_concept_analysis/blob/HEAD/alignment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6386836e08b5639"}},{"code_sha256_prefix":"f677210d73134f56","entry":"load_clusters","repo":"qcri/latent_concept_analysis","repo_kind":"official","path":"alignment.py","file_url":"https://github.com/qcri/latent_concept_analysis/blob/HEAD/alignment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f677210d73134f56"}},{"code_sha256_prefix":"2cf1d9d9992bd9fc","entry":"load_sentences_and_labels","repo":"qcri/latent_concept_analysis","repo_kind":"official","path":"alignment.py","file_url":"https://github.com/qcri/latent_concept_analysis/blob/HEAD/alignment.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2cf1d9d9992bd9fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}