{"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/revisiting-in-context-learning-inference","title":"Revisiting In-context Learning Inference Circuit in Large Language Models","arxiv_id":"2410.04468","date":"2024-10-06","proceeding":null,"authors":["Hakaze Cho","Mariko Kato","Yoshihiro Sakai","Naoya Inoue"],"abstract":"In-context Learning (ICL) is an emerging few-shot learning paradigm on Language Models (LMs) with inner mechanisms un-explored. There are already existing works describing the inner processing of ICL, while they struggle to capture all the inference phenomena in large language models. Therefore, this paper proposes a comprehensive circuit to model the inference dynamics and try to explain the observed phenomena of ICL. In detail, we divide ICL inference into 3 major operations: (1) Input Text Encode: LMs encode every input text (demonstrations and queries) into linear representation in the hidden states with sufficient information to solve ICL tasks. (2) Semantics Merge: LMs merge the encoded representations of demonstrations with their corresponding label tokens to produce joint representations of labels and demonstrations. (3) Feature Retrieval and Copy: LMs search the joint representations similar to the query representation on a task subspace, and copy the searched representations into the query. Then, language model heads capture these copied label representations to a certain extent and decode them into predicted labels. The proposed inference circuit successfully captured many phenomena observed during the ICL process, making it a comprehensive and practical explanation of the ICL inference process. Moreover, ablation analysis by disabling the proposed steps seriously damages the ICL performance, suggesting the proposed inference circuit is a dominating mechanism. Additionally, we confirm and list some bypass mechanisms that solve ICL tasks in parallel with the proposed circuit.","url_abs":"https://arxiv.org/abs/2410.04468v3","url_pdf":"https://arxiv.org/pdf/2410.04468v3.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":"revisiting-in-context-learning-inference","repo_url":"https://github.com/hc495/ICL_Circuit","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.04468","atlas_url":"https://app.syntology.ai/?focus=2410.04468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04468"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.04468"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.04468"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.04468\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2410.04468"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.04468\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.04468"},"call":"get_concepts_for_paper(arxiv_id=\"2410.04468\")"}],"by_repo":[{"repo":"hc495/ICL_Circuit","kind":"official","samples":15,"ran":11,"instrument":0,"unverified":4}],"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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2410.04468.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2410.04468.svg"},"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/hc495/ICL_Circuit","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":10,"ran_honours":1,"unverified":4},"n_samples":15,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":15,"ran":11,"n_ran_checked":11,"n_instrument":0,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":11,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"6d2ba9201e0266c1","code_sha256_prefix":"6d2ba9201e0266c1","entry":"ICL_inference_to_hidden_states","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/inference.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, tokenizer:callable/0/?, prompts:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6d2ba9201e0266c1"}},{"code_sha256":"0e4a9d80be097eab","code_sha256_prefix":"0e4a9d80be097eab","entry":"ICL_inference_to_hidden_states_transposed","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/inference.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, tokenizer:callable/0/?, prompts:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0e4a9d80be097eab"}},{"code_sha256":"03f5ae8eefe2ed8f","code_sha256_prefix":"03f5ae8eefe2ed8f","entry":"encoder_inference_to_feature","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/inference.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, tokenizer:callable/0/?, queries:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"03f5ae8eefe2ed8f"}},{"code_sha256":"dc2a498623d25b35","code_sha256_prefix":"dc2a498623d25b35","entry":"find_tokenized_label_word","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/ablation_study.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/ablation_study.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tokenizer:callable/0/?, experimentor:MockExperimentor/0/?, prompt:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"dc2a498623d25b35"}},{"code_sha256":"ab0facc671844bd0","code_sha256_prefix":"ab0facc671844bd0","entry":"get_induction_correctness_for_single_layer","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/induction_evaluation.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/induction_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"ICL_attention:dict/0/?, experimentor:MockExperimentor/0/?, sample_index:int/0/int, layer:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ab0facc671844bd0"}},{"code_sha256":"36830c7e7fd81df1","code_sha256_prefix":"36830c7e7fd81df1","entry":"get_induction_magnitude_for_single_layer","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/induction_evaluation.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/induction_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"ICL_attention:list/1/list, experimentor:Experimentor/0/?, sample_index:int/0/int, layer:int/0/int","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"36830c7e7fd81df1"}},{"code_sha256":"61a2e6dfc5a9fe1f","code_sha256_prefix":"61a2e6dfc5a9fe1f","entry":"kernel_alignment","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/kernel_alignment.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/kernel_alignment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"simGraph_1:ndarray/2/float, simGraph_2:ndarray/2/float, k:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"61a2e6dfc5a9fe1f"}},{"code_sha256":"638cfdf35bdeb6ba","code_sha256_prefix":"638cfdf35bdeb6ba","entry":"load_data_from_StaICC_experimentor","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/load_model_and_data.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/load_model_and_data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"experimentor:MockExperimentor/0/?, prompt_cut:str/0/str, target_label_correction:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"638cfdf35bdeb6ba"}},{"code_sha256":"5d93a88b24afc491","code_sha256_prefix":"5d93a88b24afc491","entry":"overlap","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/kernel_alignment.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/kernel_alignment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"a:list/1/int, b:list/1/int","fixture_out_type":"int","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5d93a88b24afc491"},"code_page":"/code/overlap","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5d93a88b24afc491"}},{"code_sha256":"81967b2af6f55803","code_sha256_prefix":"81967b2af6f55803","entry":"sim_graph","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/kernel_alignment.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/kernel_alignment.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"features:ndarray/2/float","fixture_out_type":"list","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"81967b2af6f55803"}},{"code_sha256":"3a45ae8b2ab1d6e9","code_sha256_prefix":"3a45ae8b2ab1d6e9","entry":"tokenized_length","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/induction_evaluation.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/induction_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tokenizer:callable/0/?, prompt:str/0/str","fixture_out_type":"int","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3a45ae8b2ab1d6e9"}},{"code_sha256":"8ac576595ccbc620","code_sha256_prefix":"8ac576595ccbc620","entry":"Masked_ICL_inference","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/ablation_study.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/ablation_study.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8ac576595ccbc620"}},{"code_sha256":"ab89dd08b607b43c","code_sha256_prefix":"ab89dd08b607b43c","entry":"head_ablation","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/ablation_study.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/ablation_study.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ab89dd08b607b43c"}},{"code_sha256":"f906d6d0f7a495ad","code_sha256_prefix":"f906d6d0f7a495ad","entry":"load_ICL_model","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/load_model_and_data.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/load_model_and_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f906d6d0f7a495ad"}},{"code_sha256":"fdf0bd39d2cf5fed","code_sha256_prefix":"fdf0bd39d2cf5fed","entry":"load_encode_model","repo":"hc495/ICL_Circuit","repo_kind":"official","path":"util/load_model_and_data.py","file_url":"https://github.com/hc495/ICL_Circuit/blob/HEAD/util/load_model_and_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fdf0bd39d2cf5fed"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"887f1bc37b996d9e3f24303289c4d445a280bca70f14c6b7244c2620a1862b00","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}