{"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/effective-skill-unlearning-through","title":"Effective Skill Unlearning through Intervention and Abstention","arxiv_id":"2503.21730","date":"2025-03-27","proceeding":null,"authors":["Yongce Li","Chung-En Sun","Tsui-Wei Weng"],"abstract":"Large language Models (LLMs) have demonstrated remarkable skills across various domains. Understanding the mechanisms behind their abilities and implementing controls over them is becoming increasingly important for developing better models. In this paper, we focus on skill unlearning in LLMs, specifically unlearning a particular skill while retaining their overall capabilities. We introduce two lightweight, training-free machine skill unlearning techniques for LLMs. First, we observe that the pre-activation distribution of neurons in each Feed-Forward Layer (FFL) differs when the model demonstrates different skills. Additionally, we find that queries triggering the same skill cluster within the FFL key space and can be separated from other queries using a hypercube. Based on these observations, we propose two lightweight, training-free skill unlearning methods via \\textit{intervention} and \\textit{abstention} respectively: \\texttt{Neuron Adjust} and \\texttt{Key Space Detection}. We evaluate our methods on unlearning math-solving, Python-coding, and comprehension skills across seven different languages. The results demonstrate their strong unlearning capabilities for the designated skills. Specifically, \\texttt{Key Space Detection} achieves over 80\\% relative performance drop on the forgetting skill and less than 10\\% relative performance drop on other skills and the model's general knowledge (MMLU) for most unlearning tasks. Our code is available at https://github.com/Trustworthy-ML-Lab/effective_skill_unlearning","url_abs":"https://arxiv.org/abs/2503.21730v2","url_pdf":"https://arxiv.org/pdf/2503.21730v2.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":"effective-skill-unlearning-through","repo_url":"https://github.com/trustworthy-ml-lab/effective_skill_unlearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"mmlu","task_name":"MMLU"},{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.21730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21730"}},"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/trustworthy-ml-lab/effective_skill_unlearning","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Trustworthy-ML-Lab/effective_skill_unlearning","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"d14b3a58617f1b90","entry":"get_neuron_mean_std_adjust_info","repo":"Trustworthy-ML-Lab/effective_skill_unlearning","repo_kind":"official","path":"get_adjust_info.py","file_url":"https://github.com/Trustworthy-ML-Lab/effective_skill_unlearning/blob/HEAD/get_adjust_info.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d14b3a58617f1b90"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}