{"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/instruct-and-extract-instruction-tuning-for","title":"Instruct and Extract: Instruction Tuning for On-Demand Information Extraction","arxiv_id":"2310.16040","date":"2023-10-24","proceeding":null,"authors":["Yizhu Jiao","Ming Zhong","Sha Li","Ruining Zhao","Siru Ouyang","Heng Ji","Jiawei Han"],"abstract":"Large language models with instruction-following capabilities open the door to a wider group of users. However, when it comes to information extraction - a classic task in natural language processing - most task-specific systems cannot align well with long-tail ad hoc extraction use cases for non-expert users. To address this, we propose a novel paradigm, termed On-Demand Information Extraction, to fulfill the personalized demands of real-world users. Our task aims to follow the instructions to extract the desired content from the associated text and present it in a structured tabular format. The table headers can either be user-specified or inferred contextually by the model. To facilitate research in this emerging area, we present a benchmark named InstructIE, inclusive of both automatically generated training data, as well as the human-annotated test set. Building on InstructIE, we further develop an On-Demand Information Extractor, ODIE. Comprehensive evaluations on our benchmark reveal that ODIE substantially outperforms the existing open-source models of similar size. Our code and dataset are released on https://github.com/yzjiao/On-Demand-IE.","url_abs":"https://arxiv.org/abs/2310.16040v1","url_pdf":"https://arxiv.org/pdf/2310.16040v1.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":"instruct-and-extract-instruction-tuning-for","repo_url":"https://github.com/yzjiao/on-demand-ie","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"hoc","method_name":"HOC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.16040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16040"}},"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/yzjiao/on-demand-ie","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/yzjiao/On-Demand-IE","reach":{"status":"ok"}}],"summary":{"ran":11,"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"official":{"samples":21,"ran":12,"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":21,"samples":[{"code_sha256_prefix":"ef6252d46de7c7cc","entry":"Prompter","repo":"yzjiao/On-Demand-IE","repo_kind":"official","path":"training/inference.py","file_url":"https://github.com/yzjiao/On-Demand-IE/blob/HEAD/training/inference.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":"ef6252d46de7c7cc"}},{"code_sha256_prefix":"6b370c595a81b22a","entry":"extract_markdown","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"evaluation/rougel_for_content.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/evaluation/rougel_for_content.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":"6b370c595a81b22a"}},{"code_sha256_prefix":"052514aef99856ca","entry":"get_score","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"evaluation/rougel_for_content.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/evaluation/rougel_for_content.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":"052514aef99856ca"}},{"code_sha256_prefix":"66a05762df9f31f6","entry":"is_markdown_table","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/filter_table.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/filter_table.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":"66a05762df9f31f6"}},{"code_sha256_prefix":"10795bb334d402c7","entry":"is_markdown_table","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/filter_table_random.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/filter_table_random.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":"10795bb334d402c7"}},{"code_sha256_prefix":"5f77c565b5e3db71","entry":"load_data","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/filter_table.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/filter_table.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":"5f77c565b5e3db71"}},{"code_sha256_prefix":"24e7ec1a7a9f90db","entry":"load_data","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_fixed_instruction.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_fixed_instruction.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":"24e7ec1a7a9f90db"}},{"code_sha256_prefix":"71c2752e634dfab4","entry":"load_data","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_table_cot.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_table_cot.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":"71c2752e634dfab4"}},{"code_sha256_prefix":"70c53f6127609f82","entry":"load_json","repo":"yzjiao/On-Demand-IE","repo_kind":"official","path":"training/inference.py","file_url":"https://github.com/yzjiao/On-Demand-IE/blob/HEAD/training/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"70c53f6127609f82"}},{"code_sha256_prefix":"e45c55264dd5b82f","entry":"markdown2dic","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/filter_table.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/filter_table.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":"e45c55264dd5b82f"}},{"code_sha256_prefix":"d29e55e9025baada","entry":"remove_blank_lines","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/paraphrase_instruction.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/paraphrase_instruction.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":"d29e55e9025baada"}},{"code_sha256_prefix":"bb3d06806aaa4310","entry":"remove_numbered_sentences","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/paraphrase_instruction.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/paraphrase_instruction.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":"bb3d06806aaa4310"}},{"code_sha256_prefix":"1aac48e34c958bec","entry":"gene_open_instr","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_open_instruction.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_open_instruction.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":"1aac48e34c958bec"}},{"code_sha256_prefix":"638a9c1d5efb3f28","entry":"generate_chat_completion","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_fixed_instruction.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_fixed_instruction.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":"638a9c1d5efb3f28"}},{"code_sha256_prefix":"4b24b509e88000c1","entry":"generate_chat_completion","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_open_instruction.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_open_instruction.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":"4b24b509e88000c1"}},{"code_sha256_prefix":"38e5559b19e9cbed","entry":"generate_chat_completion","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_table.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_table.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":"38e5559b19e9cbed"}},{"code_sha256_prefix":"bc33c96835cef11d","entry":"generate_instruction","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_fixed_instruction.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_fixed_instruction.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":"bc33c96835cef11d"}},{"code_sha256_prefix":"d1ebb5f91c8f27d7","entry":"generate_table","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_table.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_table.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":"d1ebb5f91c8f27d7"}},{"code_sha256_prefix":"786d7aed7211909e","entry":"generate_table","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_table_cot.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_table_cot.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":"786d7aed7211909e"}},{"code_sha256_prefix":"a6f428fed9e294b0","entry":"generate_text","repo":"yzjiao/on-demand-ie","repo_kind":"official","path":"data_generation/generate_text.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_text.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":"a6f428fed9e294b0"}},{"code_sha256_prefix":"a64c18f13070bb1b","entry":"main","repo":"yzjiao/On-Demand-IE","repo_kind":"official","path":"training/inference.py","file_url":"https://github.com/yzjiao/On-Demand-IE/blob/HEAD/training/inference.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":"a64c18f13070bb1b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}