{"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/modeling-legal-reasoning-lm-annotation-at-the","title":"Modeling Legal Reasoning: LM Annotation at the Edge of Human Agreement","arxiv_id":"2310.18440","date":"2023-10-27","proceeding":null,"authors":["Rosamond Thalken","Edward H. Stiglitz","David Mimno","Matthew Wilkens"],"abstract":"Generative language models (LMs) are increasingly used for document class-prediction tasks and promise enormous improvements in cost and efficiency. Existing research often examines simple classification tasks, but the capability of LMs to classify on complex or specialized tasks is less well understood. We consider a highly complex task that is challenging even for humans: the classification of legal reasoning according to jurisprudential philosophy. Using a novel dataset of historical United States Supreme Court opinions annotated by a team of domain experts, we systematically test the performance of a variety of LMs. We find that generative models perform poorly when given instructions (i.e. prompts) equal to the instructions presented to human annotators through our codebook. Our strongest results derive from fine-tuning models on the annotated dataset; the best performing model is an in-domain model, LEGAL-BERT. We apply predictions from this fine-tuned model to study historical trends in jurisprudence, an exercise that both aligns with prominent qualitative historical accounts and points to areas of possible refinement in those accounts. Our findings generally sound a note of caution in the use of generative LMs on complex tasks without fine-tuning and point to the continued relevance of human annotation-intensive classification methods.","url_abs":"https://arxiv.org/abs/2310.18440v1","url_pdf":"https://arxiv.org/pdf/2310.18440v1.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":"modeling-legal-reasoning-lm-annotation-at-the","repo_url":"https://github.com/rosthalken/legal-interpretation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"jurisprudence","task_name":"Jurisprudence"},{"task_slug":"legal-reasoning","task_name":"Legal Reasoning"},{"task_slug":"philosophy","task_name":"Philosophy"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.18440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18440"}},"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/rosthalken/legal-interpretation","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"b305b281072ece66","entry":"clean_text","repo":"rosthalken/legal-interpretation","repo_kind":"official","path":"create_samples.py","file_url":"https://github.com/rosthalken/legal-interpretation/blob/HEAD/create_samples.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":"b305b281072ece66"}},{"code_sha256_prefix":"f60597a9de3e6501","entry":"compute_metrics","repo":"rosthalken/legal-interpretation","repo_kind":"official","path":"train_model.py","file_url":"https://github.com/rosthalken/legal-interpretation/blob/HEAD/train_model.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":"f60597a9de3e6501"}},{"code_sha256_prefix":"6a7eceaef502e02c","entry":"load_file","repo":"rosthalken/legal-interpretation","repo_kind":"official","path":"create_samples.py","file_url":"https://github.com/rosthalken/legal-interpretation/blob/HEAD/create_samples.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":"6a7eceaef502e02c"}},{"code_sha256_prefix":"7ea6699b44cb0d86","entry":"load_file","repo":"rosthalken/legal-interpretation","repo_kind":"official","path":"prep_predictions.py","file_url":"https://github.com/rosthalken/legal-interpretation/blob/HEAD/prep_predictions.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":"7ea6699b44cb0d86"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}