{"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/adelie-aligning-large-language-models-on","title":"ADELIE: Aligning Large Language Models on Information Extraction","arxiv_id":"2405.05008","date":"2024-05-08","proceeding":null,"authors":["Yunjia Qi","Hao Peng","Xiaozhi Wang","Bin Xu","Lei Hou","Juanzi Li"],"abstract":"Large language models (LLMs) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks. This primarily arises from LLMs not being aligned with humans, as mainstream alignment datasets typically do not include IE data. In this paper, we introduce ADELIE (Aligning large language moDELs on Information Extraction), an aligned LLM that effectively solves various IE tasks, including closed IE, open IE, and on-demand IE. We first collect and construct a high-quality alignment corpus IEInstruct for IE. Then we train ADELIE_SFT using instruction tuning on IEInstruct. We further train ADELIE_SFT with direct preference optimization (DPO) objective, resulting in ADELIE_DPO. Extensive experiments on various held-out IE datasets demonstrate that our models (ADELIE_SFT and ADELIE_DPO) achieve state-of-the-art (SoTA) performance among open-source models. We further explore the general capabilities of ADELIE, and experimental results reveal that their general capabilities do not exhibit a noticeable decline. We will release the code, data, and models to facilitate further research.","url_abs":"https://arxiv.org/abs/2405.05008v2","url_pdf":"https://arxiv.org/pdf/2405.05008v2.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":"adelie-aligning-large-language-models-on","repo_url":"https://github.com/THU-KEG/ADELIE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.05008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05008"}},"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-KEG/ADELIE","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":11},"by_repo_kind":{"official":{"samples":18,"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":18,"samples":[{"code_sha256_prefix":"bd6665195c202c96","entry":"concatenated_forward","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/dpo_utils.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/dpo_utils.py","link_basis":"harvester_set","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":"bd6665195c202c96"}},{"code_sha256_prefix":"98be928ee5a8a3bd","entry":"concatenated_inputs","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/dpo_utils.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/dpo_utils.py","link_basis":"harvester_set","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":"98be928ee5a8a3bd"}},{"code_sha256_prefix":"17d17a8f4a188a7d","entry":"convert_message","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/gradio_demo_chat.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/gradio_demo_chat.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":"17d17a8f4a188a7d"}},{"code_sha256_prefix":"538471327537d426","entry":"create_prompt_with_llama2_chat_format","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/eval/templates.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/eval/templates.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":"538471327537d426"}},{"code_sha256_prefix":"45e2cc1022c95249","entry":"create_prompt_with_olmo_chat_format","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/eval/templates.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/eval/templates.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":"45e2cc1022c95249"}},{"code_sha256_prefix":"b2b6de249cebe189","entry":"dpo_loss","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/dpo_utils.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/dpo_utils.py","link_basis":"harvester_set","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":"b2b6de249cebe189"}},{"code_sha256_prefix":"97229c97d4273595","entry":"encode_with_messages_format","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/finetune.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/finetune.py","link_basis":"harvester_set","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":"97229c97d4273595"}},{"code_sha256_prefix":"697d92a5d51eff3e","entry":"create_prompt_with_tulu_chat_format","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/eval/templates.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/eval/templates.py","link_basis":"harvester_set","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":"697d92a5d51eff3e"}},{"code_sha256_prefix":"dcad9ac62979ca49","entry":"dispatch_openai_chat_requesets","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/eval/dispatch_openai_requests.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/eval/dispatch_openai_requests.py","link_basis":"harvester_set","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":"dcad9ac62979ca49"}},{"code_sha256_prefix":"71e4259026911444","entry":"dispatch_openai_prompt_requesets","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/eval/dispatch_openai_requests.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/eval/dispatch_openai_requests.py","link_basis":"harvester_set","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":"71e4259026911444"}},{"code_sha256_prefix":"96351a65183bb428","entry":"encode_few_shot_example","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/instruction_encode_templates.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/instruction_encode_templates.py","link_basis":"harvester_set","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":"96351a65183bb428"}},{"code_sha256_prefix":"f839fd4c6f96a26f","entry":"encode_instruction_example","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/instruction_encode_templates.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/instruction_encode_templates.py","link_basis":"harvester_set","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":"f839fd4c6f96a26f"}},{"code_sha256_prefix":"5966cc3120c46d61","entry":"encode_with_prompt_completion_format","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/finetune.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/finetune.py","link_basis":"harvester_set","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":"5966cc3120c46d61"}},{"code_sha256_prefix":"cdbcc01805fac313","entry":"generate_completions","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/eval/utils.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/eval/utils.py","link_basis":"harvester_set","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":"cdbcc01805fac313"}},{"code_sha256_prefix":"d134c88af0236263","entry":"get_next_word_predictions","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/eval/utils.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/eval/utils.py","link_basis":"harvester_set","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":"d134c88af0236263"}},{"code_sha256_prefix":"533568a0e86ef298","entry":"get_statistics_for_messages_data","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/get_statistics.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/get_statistics.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":"533568a0e86ef298"}},{"code_sha256_prefix":"84aeb6a7586885f5","entry":"get_statistics_for_prompt_completion_data","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/open_instruct/get_statistics.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/open_instruct/get_statistics.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":"84aeb6a7586885f5"}},{"code_sha256_prefix":"d029fa02758da921","entry":"score_completions","repo":"THU-KEG/ADELIE","repo_kind":"official","path":"train4llama/eval/utils.py","file_url":"https://github.com/THU-KEG/ADELIE/blob/HEAD/train4llama/eval/utils.py","link_basis":"harvester_set","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":"d029fa02758da921"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}