{"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/beyond-single-concept-vector-modeling-concept","title":"Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution","arxiv_id":"2410.00153","date":"2024-09-30","proceeding":null,"authors":["Haiyan Zhao","Heng Zhao","Bo Shen","Ali Payani","Fan Yang","Mengnan Du"],"abstract":"Probing learned concepts in large language models (LLMs) is crucial for understanding how semantic knowledge is encoded internally. Training linear classifiers on probing tasks is a principle approach to denote the vector of a certain concept in the representation space. However, the single vector identified for a concept varies with both data and training, making it less robust and weakening its effectiveness in real-world applications. To address this challenge, we propose an approach to approximate the subspace representing a specific concept. Built on linear probing classifiers, we extend the concept vectors into Gaussian Concept Subspace (GCS). We demonstrate GCS's effectiveness through measuring its faithfulness and plausibility across multiple LLMs with different sizes and architectures. Additionally, we use representation intervention tasks to showcase its efficacy in real-world applications such as emotion steering. Experimental results indicate that GCS concept vectors have the potential to balance steering performance and maintaining the fluency in natural language generation tasks.","url_abs":"https://arxiv.org/abs/2410.00153v3","url_pdf":"https://arxiv.org/pdf/2410.00153v3.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":"beyond-single-concept-vector-modeling-concept","repo_url":"https://github.com/hy-zhao23/gcs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.00153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00153"}},"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/hy-zhao23/GCS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hy-zhao23/gcs","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"e93d200bb8d852d6","entry":"cos_sim_matrix","repo":"hy-zhao23/GCS","repo_kind":"official","path":"utils/algo.py","file_url":"https://github.com/hy-zhao23/GCS/blob/HEAD/utils/algo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e93d200bb8d852d6"}},{"code_sha256_prefix":"1871430c44b7a75d","entry":"extract","repo":"hy-zhao23/GCS","repo_kind":"official","path":"preprocess/generate_text.py","file_url":"https://github.com/hy-zhao23/GCS/blob/HEAD/preprocess/generate_text.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1871430c44b7a75d"}},{"code_sha256_prefix":"90ba157cde9eb688","entry":"one_std_estimation","repo":"hy-zhao23/GCS","repo_kind":"official","path":"utils/algo.py","file_url":"https://github.com/hy-zhao23/GCS/blob/HEAD/utils/algo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"90ba157cde9eb688"}},{"code_sha256_prefix":"b4fa3ff979015f08","entry":"vectors_similarity","repo":"hy-zhao23/GCS","repo_kind":"official","path":"utils/algo.py","file_url":"https://github.com/hy-zhao23/GCS/blob/HEAD/utils/algo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4fa3ff979015f08"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}