{"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/let-s-learn-step-by-step-enhancing-in-context","title":"Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning","arxiv_id":"2402.10738","date":"2024-02-16","proceeding":null,"authors":["Yinpeng Liu","Jiawei Liu","Xiang Shi","Qikai Cheng","Yong Huang","Wei Lu"],"abstract":"Demonstration ordering, which is an important strategy for in-context learning (ICL), can significantly affects the performance of large language models (LLMs). However, most of the current approaches of ordering require high computational costs to introduce the priori knowledge. In this paper, inspired by the human learning process, we propose a simple but effective demonstration ordering method for ICL, named the few-shot In-Context Curriculum Learning (ICCL). The ICCL implies gradually increasing the complexity of prompt demonstrations during the inference process. The difficulty can be assessed by human experts or LLMs-driven metrics, such as perplexity. Then we design extensive experiments to discuss the effectiveness of the ICCL at both corpus-level and instance-level. Moreover, we also investigate the formation mechanism of LLM's ICCL capability. Experimental results demonstrate that ICCL, developed during the instruction-tuning stage, is effective for representative open-source LLMs. To facilitate further research and applications by other scholars, we make the code publicly available.","url_abs":"https://arxiv.org/abs/2402.10738v2","url_pdf":"https://arxiv.org/pdf/2402.10738v2.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":"let-s-learn-step-by-step-enhancing-in-context","repo_url":"https://github.com/61peng/curri_learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2402.10738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10738"}},"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/61peng/curri_learning","reach":{"status":"ok"}}],"summary":{"ran":5,"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":8,"samples":[{"code_sha256_prefix":"a0eacdee84b33bd8","entry":"get_choice_sep","repo":"61peng/curri_learning","repo_kind":"official","path":"src/datasets/instructions.py","file_url":"https://github.com/61peng/curri_learning/blob/HEAD/src/datasets/instructions.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":"a0eacdee84b33bd8"}},{"code_sha256_prefix":"790c0d445bff422d","entry":"get_length","repo":"61peng/curri_learning","repo_kind":"official","path":"src/dataset_readers/inference_dsr.py","file_url":"https://github.com/61peng/curri_learning/blob/HEAD/src/dataset_readers/inference_dsr.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"790c0d445bff422d"}},{"code_sha256_prefix":"ec8412213576908e","entry":"get_sequence","repo":"61peng/curri_learning","repo_kind":"official","path":"script/one_stage.py","file_url":"https://github.com/61peng/curri_learning/blob/HEAD/script/one_stage.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":"ec8412213576908e"}},{"code_sha256_prefix":"e6765d84a7746f7e","entry":"get_task_type","repo":"61peng/curri_learning","repo_kind":"official","path":"src/datasets/instructions.py","file_url":"https://github.com/61peng/curri_learning/blob/HEAD/src/datasets/instructions.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":"e6765d84a7746f7e"}},{"code_sha256_prefix":"8d56b3db40af6433","entry":"get_template","repo":"61peng/curri_learning","repo_kind":"official","path":"src/datasets/instructions.py","file_url":"https://github.com/61peng/curri_learning/blob/HEAD/src/datasets/instructions.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":"8d56b3db40af6433"}},{"code_sha256_prefix":"2cb3cc8f296674aa","entry":"set_field","repo":"61peng/curri_learning","repo_kind":"official","path":"src/dataset_readers/ppl_inference_cls_dsr.py","file_url":"https://github.com/61peng/curri_learning/blob/HEAD/src/dataset_readers/ppl_inference_cls_dsr.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":"2cb3cc8f296674aa"}},{"code_sha256_prefix":"c6a696c2588c1845","entry":"set_length","repo":"61peng/curri_learning","repo_kind":"official","path":"src/dataset_readers/inference_dsr.py","file_url":"https://github.com/61peng/curri_learning/blob/HEAD/src/dataset_readers/inference_dsr.py","link_basis":"plan_row","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":"c6a696c2588c1845"}},{"code_sha256_prefix":"4588f09a37f2c0bd","entry":"set_length","repo":"61peng/curri_learning","repo_kind":"official","path":"src/dataset_readers/ppl_inference_cls_dsr.py","file_url":"https://github.com/61peng/curri_learning/blob/HEAD/src/dataset_readers/ppl_inference_cls_dsr.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4588f09a37f2c0bd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}