{"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/natural-instructions-benchmarking","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","arxiv_id":"2104.08773","date":"2021-04-18","proceeding":"ACL 2022 5","authors":["Swaroop Mishra","Daniel Khashabi","Chitta Baral","Hannaneh Hajishirzi"],"abstract":"Humans (e.g., crowdworkers) have a remarkable ability in solving different tasks, by simply reading textual instructions that define them and looking at a few examples. Despite the success of the conventional supervised learning on individual datasets, such models often struggle with generalization across tasks (e.g., a question-answering system cannot solve classification tasks). A long-standing challenge in AI is to build a model that learns a new task by understanding the human-readable instructions that define it. To study this, we introduce NATURAL INSTRUCTIONS, a dataset of 61 distinct tasks, their human-authored instructions, and 193k task instances (input-output pairs). The instructions are obtained from crowdsourcing instructions used to create existing NLP datasets and mapped to a unified schema. Using this meta-dataset, we measure cross-task generalization by training models on seen tasks and measuring generalization to the remaining unseen ones. We adopt generative pre-trained language models to encode task-specific instructions along with input and generate task output. Our results indicate that models benefit from instructions when evaluated in terms of generalization to unseen tasks (19% better for models utilizing instructions). These models, however, are far behind an estimated performance upperbound indicating significant room for more progress in this direction.","url_abs":"https://arxiv.org/abs/2104.08773v4","url_pdf":"https://arxiv.org/pdf/2104.08773v4.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":"natural-instructions-benchmarking","repo_url":"https://github.com/allenai/natural-instructions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"natural-instructions-benchmarking","repo_url":"https://github.com/allenai/natural-instructions-v1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"natural-instructions-benchmarking","repo_url":"https://github.com/allenai/natural-instructions-expansion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[{"slug":"natural-instructions","name":"Natural Instructions","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08773"}},"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/allenai/natural-instructions","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenai/natural-instructions-expansion","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenai/natural-instructions-v1","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":1,"samples":[{"code_sha256_prefix":"6dbf1b2a5b901370","entry":"atoi","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"6dbf1b2a5b901370"}},{"code_sha256_prefix":"bd0663420f30898a","entry":"dict_raise_on_duplicates","repo":"allenai/natural-instructions","repo_kind":"official","path":"src/test_all.py","file_url":"https://github.com/allenai/natural-instructions/blob/HEAD/src/test_all.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd0663420f30898a"}},{"code_sha256_prefix":"a014ee63e1056f19","entry":"encodeinstruction","repo":"allenai/natural-instructions-v1","repo_kind":"official","path":"src/utils/encodeinstruction.py","file_url":"https://github.com/allenai/natural-instructions-v1/blob/HEAD/src/utils/encodeinstruction.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a014ee63e1056f19"}},{"code_sha256_prefix":"866c94d120eb077d","entry":"extract_categories","repo":"allenai/natural-instructions","repo_kind":"official","path":"src/test_all.py","file_url":"https://github.com/allenai/natural-instructions/blob/HEAD/src/test_all.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"866c94d120eb077d"}},{"code_sha256_prefix":"6829ceb72569fa12","entry":"metric_max_over_ground_truths","repo":"allenai/natural-instructions-v1","repo_kind":"official","path":"src/evaluation.py","file_url":"https://github.com/allenai/natural-instructions-v1/blob/HEAD/src/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6829ceb72569fa12"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}