{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/studying-large-language-model-generalization","title":"Studying Large Language Model Generalization with Influence Functions","arxiv_id":"2308.03296","date":"2023-08-07","proceeding":null,"authors":["Roger Grosse","Juhan Bae","Cem Anil","Nelson Elhage","Alex Tamkin","Amirhossein Tajdini","Benoit Steiner","Dustin Li","Esin Durmus","Ethan Perez","Evan Hubinger","Kamilė Lukošiūtė","Karina Nguyen","Nicholas Joseph","Sam McCandlish","Jared Kaplan","Samuel R. Bowman"],"abstract":"When trying to gain better visibility into a machine learning model in order to understand and mitigate the associated risks, a potentially valuable source of evidence is: which training examples most contribute to a given behavior? Influence functions aim to answer a counterfactual: how would the model's parameters (and hence its outputs) change if a given sequence were added to the training set? While influence functions have produced insights for small models, they are difficult to scale to large language models (LLMs) due to the difficulty of computing an inverse-Hessian-vector product (IHVP). We use the Eigenvalue-corrected Kronecker-Factored Approximate Curvature (EK-FAC) approximation to scale influence functions up to LLMs with up to 52 billion parameters. In our experiments, EK-FAC achieves similar accuracy to traditional influence function estimators despite the IHVP computation being orders of magnitude faster. We investigate two algorithmic techniques to reduce the cost of computing gradients of candidate training sequences: TF-IDF filtering and query batching. We use influence functions to investigate the generalization patterns of LLMs, including the sparsity of the influence patterns, increasing abstraction with scale, math and programming abilities, cross-lingual generalization, and role-playing behavior. Despite many apparently sophisticated forms of generalization, we identify a surprising limitation: influences decay to near-zero when the order of key phrases is flipped. Overall, influence functions give us a powerful new tool for studying the generalization properties of LLMs.","url_abs":"https://arxiv.org/abs/2308.03296v1","url_pdf":"https://arxiv.org/pdf/2308.03296v1.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":"studying-large-language-model-generalization","repo_url":"https://github.com/jacksonwuxs/usablexai_llm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"studying-large-language-model-generalization","repo_url":"https://github.com/pomonam/kronfluence","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"studying-large-language-model-generalization","repo_url":"https://github.com/ztcoalson/if-guide","is_official":0,"mentioned_in_paper":0,"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":"math","task_name":"Math"},{"task_slug":null,"task_name":"counterfactual"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.03296","atlas_url":"https://app.syntology.ai/?focus=2308.03296","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2308.03296"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2308.03296\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2308.03296"},"call":"get_concepts_for_paper(arxiv_id=\"2308.03296\")"}],"by_repo":[{"repo":"jacksonwuxs/usablexai_llm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.08946"],"harvested_for_calls":[{"arxiv_id":"2403.08946","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.08946"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.08946\")"}]},{"repo":"pomonam/kronfluence","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1503.05671"],"harvested_for_calls":[{"arxiv_id":"1503.05671","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1503.05671"},"call":"get_harvested_code_for_paper(arxiv_id=\"1503.05671\")"}]},{"repo":"ztcoalson/if-guide","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2506.01790"],"harvested_for_calls":[{"arxiv_id":"2506.01790","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2506.01790"},"call":"get_harvested_code_for_paper(arxiv_id=\"2506.01790\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1f06481dcda723a74d152b26bd0c14feb0971702921bd81356b0e8f7fc4def33","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}