{"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/efficient-causal-graph-discovery-using-large","title":"Efficient Causal Graph Discovery Using Large Language Models","arxiv_id":"2402.01207","date":"2024-02-02","proceeding":null,"authors":["Thomas Jiralerspong","Xiaoyin Chen","Yash More","Vedant Shah","Yoshua Bengio"],"abstract":"We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-based methods have used a pairwise query approach, this requires a quadratic number of queries which quickly becomes impractical for larger causal graphs. In contrast, the proposed framework uses a breadth-first search (BFS) approach which allows it to use only a linear number of queries. We also show that the proposed method can easily incorporate observational data when available, to improve performance. In addition to being more time and data-efficient, the proposed framework achieves state-of-the-art results on real-world causal graphs of varying sizes. The results demonstrate the effectiveness and efficiency of the proposed method in discovering causal relationships, showcasing its potential for broad applicability in causal graph discovery tasks across different domains.","url_abs":"https://arxiv.org/abs/2402.01207v4","url_pdf":"https://arxiv.org/pdf/2402.01207v4.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":"efficient-causal-graph-discovery-using-large","repo_url":"https://github.com/superkaiba/causal-llm-bfs","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":"https://syntology.ai/paper/2402.01207","atlas_url":"https://app.syntology.ai/?focus=2402.01207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01207"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/superkaiba/causal-llm-bfs","reach":{"status":"ok"}}],"summary":{"ran":10,"unverified":3},"by_repo_kind":{"official":{"samples":13,"ran":10,"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":13,"samples":[{"code_sha256_prefix":"46bfc96909c4ee22","entry":"accuracy","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/metrics.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":"46bfc96909c4ee22"}},{"code_sha256_prefix":"e4418d76e51236a7","entry":"adj_mat_to_edge_list","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"utils.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/utils.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":"e4418d76e51236a7"}},{"code_sha256_prefix":"932f6c45fffdc7c2","entry":"adjacency_matrix_to_edge_list","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"algs/llm/utils.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/algs/llm/utils.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":"932f6c45fffdc7c2"}},{"code_sha256_prefix":"2856ad4b6b397b6c","entry":"dag_to_adj_mat","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"utils.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/utils.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":"2856ad4b6b397b6c"}},{"code_sha256_prefix":"d2f102469e9957c1","entry":"get_data_prompt","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"algs/llm/bfs_prompts.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/algs/llm/bfs_prompts.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":"d2f102469e9957c1"}},{"code_sha256_prefix":"5bd72185d3deeffe","entry":"is_dag","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"utils.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/utils.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":"5bd72185d3deeffe"}},{"code_sha256_prefix":"ab810b4b69cebe75","entry":"precision","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"algs/llm/utils.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/algs/llm/utils.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":"ab810b4b69cebe75"}},{"code_sha256_prefix":"b1a73044ab13bc1a","entry":"precision","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/metrics.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":"b1a73044ab13bc1a"}},{"code_sha256_prefix":"4e1ec21825865428","entry":"recall","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"algs/llm/utils.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/algs/llm/utils.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":"4e1ec21825865428"}},{"code_sha256_prefix":"99eaef19e981c387","entry":"recall","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"metrics.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/metrics.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":"99eaef19e981c387"}},{"code_sha256_prefix":"e2b8b14caa84e2c7","entry":"llm_bfs","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"algs/llm/bfs.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/algs/llm/bfs.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":"e2b8b14caa84e2c7"}},{"code_sha256_prefix":"7f36cd5159296995","entry":"llm_pairwise","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"algs/llm/pairwise.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/algs/llm/pairwise.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":"7f36cd5159296995"}},{"code_sha256_prefix":"8121d0e3bc3faff7","entry":"notears_linear","repo":"superkaiba/causal-llm-bfs","repo_kind":"official","path":"algs/notears/linear.py","file_url":"https://github.com/superkaiba/causal-llm-bfs/blob/HEAD/algs/notears/linear.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8121d0e3bc3faff7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}