{"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/icleval-evaluating-in-context-learning","title":"ICLEval: Evaluating In-Context Learning Ability of Large Language Models","arxiv_id":"2406.14955","date":"2024-06-21","proceeding":null,"authors":["Wentong Chen","Yankai Lin","ZhenHao Zhou","HongYun Huang","Yantao Jia","Zhao Cao","Ji-Rong Wen"],"abstract":"In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Evaluating the ICL ability of LLMs can enhance their utilization and deepen our understanding of how this ability is acquired at the training stage. However, existing evaluation frameworks primarily focus on language abilities and knowledge, often overlooking the assessment of ICL ability. In this work, we introduce the ICLEval benchmark to evaluate the ICL abilities of LLMs, which encompasses two key sub-abilities: exact copying and rule learning. Through the ICLEval benchmark, we demonstrate that ICL ability is universally present in different LLMs, and model size is not the sole determinant of ICL efficacy. Surprisingly, we observe that ICL abilities, particularly copying, develop early in the pretraining process and stabilize afterward. Our source codes and benchmark are released at https://github.com/yiye3/ICLEval.","url_abs":"https://arxiv.org/abs/2406.14955v2","url_pdf":"https://arxiv.org/pdf/2406.14955v2.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":"icleval-evaluating-in-context-learning","repo_url":"https://github.com/rucbm/icleval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"icleval-evaluating-in-context-learning","repo_url":"https://github.com/yiye3/icleval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.14955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14955"}},"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/rucbm/icleval","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yiye3/icleval","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"repositories":2}},"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":"925d81f4d1098c6e","entry":"check_order","repo":"yiye3/icleval","repo_kind":"official","path":"code/generate_data/learning_ability/classifier_order.py","file_url":"https://github.com/yiye3/icleval/blob/HEAD/code/generate_data/learning_ability/classifier_order.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"925d81f4d1098c6e"}},{"code_sha256_prefix":"028f2fcce9aa8609","entry":"check_repeated_content","repo":"yiye3/icleval","repo_kind":"official","path":"code/generate_data/learning_ability/classifier_duplication.py","file_url":"https://github.com/yiye3/icleval/blob/HEAD/code/generate_data/learning_ability/classifier_duplication.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"028f2fcce9aa8609"}},{"code_sha256_prefix":"a4303b56a1de0b68","entry":"dict_search_number","repo":"yiye3/icleval","repo_kind":"official","path":"code/generate_data/copying_ability/dict_search_number.py","file_url":"https://github.com/yiye3/icleval/blob/HEAD/code/generate_data/copying_ability/dict_search_number.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4303b56a1de0b68"}},{"code_sha256_prefix":"1fa76eb617bf97a2","entry":"dict_search_string","repo":"yiye3/icleval","repo_kind":"official","path":"code/generate_data/copying_ability/dict_search_string.py","file_url":"https://github.com/yiye3/icleval/blob/HEAD/code/generate_data/copying_ability/dict_search_string.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1fa76eb617bf97a2"}},{"code_sha256_prefix":"b93732e7a9dd5f8e","entry":"find_mha_dims","repo":"yiye3/icleval","repo_kind":"official","path":"code/model_evaluation/modeling_phi/modeling_mixformer_sequential.py","file_url":"https://github.com/yiye3/icleval/blob/HEAD/code/model_evaluation/modeling_phi/modeling_mixformer_sequential.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b93732e7a9dd5f8e"}},{"code_sha256_prefix":"22644c9d1faa3ab4","entry":"get_similar_number","repo":"yiye3/icleval","repo_kind":"official","path":"code/generate_data/copying_ability/dict_search_number.py","file_url":"https://github.com/yiye3/icleval/blob/HEAD/code/generate_data/copying_ability/dict_search_number.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22644c9d1faa3ab4"}},{"code_sha256_prefix":"77d951c66faed420","entry":"load_one_sample","repo":"yiye3/icleval","repo_kind":"official","path":"code/generate_data/copying_ability/dict_search_number.py","file_url":"https://github.com/yiye3/icleval/blob/HEAD/code/generate_data/copying_ability/dict_search_number.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77d951c66faed420"}},{"code_sha256_prefix":"211c6dd070d2fd05","entry":"natural_language_string","repo":"yiye3/icleval","repo_kind":"official","path":"code/generate_data/copying_ability/natural_language_string.py","file_url":"https://github.com/yiye3/icleval/blob/HEAD/code/generate_data/copying_ability/natural_language_string.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"211c6dd070d2fd05"}},{"code_sha256_prefix":"6f2cc86ddb8c2b5b","entry":"check_format","repo":"yiye3/icleval","repo_kind":"official","path":"code/generate_data/learning_ability/classifier_format.py","file_url":"https://github.com/yiye3/icleval/blob/HEAD/code/generate_data/learning_ability/classifier_format.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f2cc86ddb8c2b5b"}},{"code_sha256_prefix":"6dd3de7ed4a93b10","entry":"greedy_until","repo":"rucbm/icleval","repo_kind":"official","path":"code/model_evaluation/run_icl_eval.py","file_url":"https://github.com/rucbm/icleval/blob/HEAD/code/model_evaluation/run_icl_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6dd3de7ed4a93b10"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}