{"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/pre-training-to-learn-in-context","title":"Pre-Training to Learn in Context","arxiv_id":"2305.09137","date":"2023-05-16","proceeding":null,"authors":["Yuxian Gu","Li Dong","Furu Wei","Minlie Huang"],"abstract":"In-context learning, where pre-trained language models learn to perform tasks from task examples and instructions in their contexts, has attracted much attention in the NLP community. However, the ability of in-context learning is not fully exploited because language models are not explicitly trained to learn in context. To this end, we propose PICL (Pre-training for In-Context Learning), a framework to enhance the language models' in-context learning ability by pre-training the model on a large collection of \"intrinsic tasks\" in the general plain-text corpus using the simple language modeling objective. PICL encourages the model to infer and perform tasks by conditioning on the contexts while maintaining task generalization of pre-trained models. We evaluate the in-context learning performance of the model trained with PICL on seven widely-used text classification datasets and the Super-NaturalInstrctions benchmark, which contains 100+ NLP tasks formulated to text generation. Our experiments show that PICL is more effective and task-generalizable than a range of baselines, outperforming larger language models with nearly 4x parameters. The code is publicly available at https://github.com/thu-coai/PICL.","url_abs":"https://arxiv.org/abs/2305.09137v1","url_pdf":"https://arxiv.org/pdf/2305.09137v1.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":"pre-training-to-learn-in-context","repo_url":"https://github.com/thu-coai/picl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.09137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09137"}},"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/thu-coai/picl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"ran":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,"samples":[{"code_sha256_prefix":"a57d1ac3e1420421","entry":"add_hp_args","repo":"thu-coai/picl","repo_kind":"official","path":"arguments.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/arguments.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":"a57d1ac3e1420421"}},{"code_sha256_prefix":"e707419fdbd20b49","entry":"add_model_config_args","repo":"thu-coai/picl","repo_kind":"official","path":"arguments.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/arguments.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":"e707419fdbd20b49"}},{"code_sha256_prefix":"ec0de3378caad0a1","entry":"add_runtime_args","repo":"thu-coai/picl","repo_kind":"official","path":"arguments.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/arguments.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":"ec0de3378caad0a1"}},{"code_sha256_prefix":"18d94355ea8f1c39","entry":"code","repo":"thu-coai/picl","repo_kind":"official","path":"data_utils/distributed_indexed.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/data_utils/distributed_indexed.py","link_basis":"plan_row","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":"18d94355ea8f1c39"}},{"code_sha256_prefix":"b5d10cd57d671759","entry":"compute_rank_metrics","repo":"thu-coai/picl","repo_kind":"official","path":"retriever.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/retriever.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":"b5d10cd57d671759"}},{"code_sha256_prefix":"bdf28f9492a770dc","entry":"data_file_path","repo":"thu-coai/picl","repo_kind":"official","path":"data_utils/distributed_indexed.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/data_utils/distributed_indexed.py","link_basis":"plan_row","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":"bdf28f9492a770dc"}},{"code_sha256_prefix":"544c348e808ef820","entry":"evaluate","repo":"thu-coai/picl","repo_kind":"official","path":"retriever.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/retriever.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":"544c348e808ef820"}},{"code_sha256_prefix":"e245194711edcd44","entry":"get_model","repo":"thu-coai/picl","repo_kind":"official","path":"evaluate_cls.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/evaluate_cls.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":"e245194711edcd44"}},{"code_sha256_prefix":"d039f1b6885abd3d","entry":"get_optimizer_params","repo":"thu-coai/picl","repo_kind":"official","path":"modeling/retriever_modeling.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/modeling/retriever_modeling.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":"d039f1b6885abd3d"}},{"code_sha256_prefix":"68777624ad9b2270","entry":"get_optimizer_params","repo":"thu-coai/picl","repo_kind":"official","path":"utils.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/utils.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":"68777624ad9b2270"}},{"code_sha256_prefix":"dbe327e3880535a1","entry":"get_tokenizer","repo":"thu-coai/picl","repo_kind":"official","path":"evaluate_cls.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/evaluate_cls.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":"dbe327e3880535a1"}},{"code_sha256_prefix":"8b1a74a6db32c163","entry":"index_file_path","repo":"thu-coai/picl","repo_kind":"official","path":"data_utils/distributed_indexed.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/data_utils/distributed_indexed.py","link_basis":"plan_row","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":"8b1a74a6db32c163"}},{"code_sha256_prefix":"6ee4fbcc1ffaa48e","entry":"string_to_float","repo":"thu-coai/picl","repo_kind":"official","path":"data_utils/data_config.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/data_utils/data_config.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":"6ee4fbcc1ffaa48e"}},{"code_sha256_prefix":"175056e6e7c4fe4a","entry":"train","repo":"thu-coai/picl","repo_kind":"official","path":"retriever.py","file_url":"https://github.com/thu-coai/picl/blob/HEAD/retriever.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":"175056e6e7c4fe4a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}