{"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/lasuie-unifying-information-extraction-with","title":"LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model","arxiv_id":"2304.06248","date":"2023-04-13","proceeding":null,"authors":["Hao Fei","Shengqiong Wu","Jingye Li","Bobo Li","Fei Li","Libo Qin","Meishan Zhang","Min Zhang","Tat-Seng Chua"],"abstract":"Universally modeling all typical information extraction tasks (UIE) with one generative language model (GLM) has revealed great potential by the latest study, where various IE predictions are unified into a linearized hierarchical expression under a GLM. Syntactic structure information, a type of effective feature which has been extensively utilized in IE community, should also be beneficial to UIE. In this work, we propose a novel structure-aware GLM, fully unleashing the power of syntactic knowledge for UIE. A heterogeneous structure inductor is explored to unsupervisedly induce rich heterogeneous structural representations by post-training an existing GLM. In particular, a structural broadcaster is devised to compact various latent trees into explicit high-order forests, helping to guide a better generation during decoding. We finally introduce a task-oriented structure fine-tuning mechanism, further adjusting the learned structures to most coincide with the end-task's need. Over 12 IE benchmarks across 7 tasks our system shows significant improvements over the baseline UIE system. Further in-depth analyses show that our GLM learns rich task-adaptive structural bias that greatly resolves the UIE crux, the long-range dependence issue and boundary identifying. Source codes are open at https://github.com/ChocoWu/LasUIE.","url_abs":"https://arxiv.org/abs/2304.06248v1","url_pdf":"https://arxiv.org/pdf/2304.06248v1.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":"lasuie-unifying-information-extraction-with","repo_url":"https://github.com/chocowu/lasuie","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"uie","task_name":"UIE"}],"methods":[{"method_slug":"glm","method_name":"GLM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.06248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06248"}},"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/chocowu/lasuie","reach":null}],"summary":{"ran_honours":1,"ran_fixture":4},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"eb29f6682a2426ad","entry":"compute_input_and_target_lengths","repo":"chocowu/lasuie","repo_kind":"official","path":"run_struct_post_train.py","file_url":"https://github.com/chocowu/lasuie/blob/HEAD/run_struct_post_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eb29f6682a2426ad"}},{"code_sha256_prefix":"7f30fc1de39e85e8","entry":"cummin","repo":"chocowu/lasuie","repo_kind":"official","path":"engine/module.py","file_url":"https://github.com/chocowu/lasuie/blob/HEAD/engine/module.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f30fc1de39e85e8"}},{"code_sha256_prefix":"a4f5f0d160d8c2c1","entry":"cumprod","repo":"chocowu/lasuie","repo_kind":"official","path":"engine/module.py","file_url":"https://github.com/chocowu/lasuie/blob/HEAD/engine/module.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4f5f0d160d8c2c1"}},{"code_sha256_prefix":"8e40a104d4067d24","entry":"cumsum","repo":"chocowu/lasuie","repo_kind":"official","path":"engine/module.py","file_url":"https://github.com/chocowu/lasuie/blob/HEAD/engine/module.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e40a104d4067d24"}},{"code_sha256_prefix":"7639bb277f652362","entry":"generate_batch_splits","repo":"chocowu/lasuie","repo_kind":"official","path":"run_struct_post_train.py","file_url":"https://github.com/chocowu/lasuie/blob/HEAD/run_struct_post_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7639bb277f652362"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}