{"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/can-llms-be-good-graph-judger-for-knowledge","title":"Can LLMs be Good Graph Judge for Knowledge Graph Construction?","arxiv_id":"2411.17388","date":"2024-11-26","proceeding":null,"authors":["Haoyu Huang","Chong Chen","Zeang Sheng","Yang Li","Wentao Zhang"],"abstract":"In real-world scenarios, most of the data obtained from the information retrieval (IR) system is unstructured. Converting natural language sentences into structured Knowledge Graphs (KGs) remains a critical challenge. We identified three limitations with respect to existing KG construction methods: (1) There could be a large amount of noise in real-world documents, which could result in extracting messy information. (2) Naive LLMs usually extract inaccurate knowledge from some domain-specific documents. (3) Hallucination phenomenon cannot be overlooked when directly using LLMs to construct KGs. In this paper, we propose \\textbf{GraphJudge}, a KG construction framework to address the aforementioned challenges. In this framework, we designed an entity-centric strategy to eliminate the noise information in the documents. And we fine-tuned a LLM as a graph judge to finally enhance the quality of generated KGs. Experiments conducted on two general and one domain-specific text-graph pair datasets demonstrate state-of-the-art performance against various baseline methods with strong generalization abilities. Our code is available at \\href{https://github.com/hhy-huang/GraphJudge}{https://github.com/hhy-huang/GraphJudge}.","url_abs":"https://arxiv.org/abs/2411.17388v3","url_pdf":"https://arxiv.org/pdf/2411.17388v3.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":"can-llms-be-good-graph-judger-for-knowledge","repo_url":"https://github.com/hhy-huang/graphjudge","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"graph-construction","task_name":"graph construction"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.17388","atlas_url":"https://app.syntology.ai/?focus=2411.17388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17388"}},"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/hhy-huang/graphjudge","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"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":"fa9b6da71c2092cf","entry":"api_model","repo":"hhy-huang/graphjudge","repo_kind":"official","path":"chat/run_chatgpt.py","file_url":"https://github.com/hhy-huang/graphjudge/blob/HEAD/chat/run_chatgpt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa9b6da71c2092cf"}},{"code_sha256_prefix":"33e9d014a6ae7fde","entry":"api_model","repo":"hhy-huang/graphjudge","repo_kind":"official","path":"chat/run_chatgpt_entity.py","file_url":"https://github.com/hhy-huang/graphjudge/blob/HEAD/chat/run_chatgpt_entity.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"33e9d014a6ae7fde"}},{"code_sha256_prefix":"0d1ca82eaad4ea6d","entry":"denoise_text","repo":"hhy-huang/graphjudge","repo_kind":"official","path":"chat/run_chatgpt_entity.py","file_url":"https://github.com/hhy-huang/graphjudge/blob/HEAD/chat/run_chatgpt_entity.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d1ca82eaad4ea6d"}},{"code_sha256_prefix":"5cc881bcb8e83712","entry":"extract_entities","repo":"hhy-huang/graphjudge","repo_kind":"official","path":"chat/run_chatgpt_entity.py","file_url":"https://github.com/hhy-huang/graphjudge/blob/HEAD/chat/run_chatgpt_entity.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cc881bcb8e83712"}},{"code_sha256_prefix":"e9255fb036722c39","entry":"generate_advanced_prompt","repo":"hhy-huang/graphjudge","repo_kind":"official","path":"graph_judger/lora_infer_batch.py","file_url":"https://github.com/hhy-huang/graphjudge/blob/HEAD/graph_judger/lora_infer_batch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9255fb036722c39"}},{"code_sha256_prefix":"e96ec96db9ef37ba","entry":"generate_prompt","repo":"hhy-huang/graphjudge","repo_kind":"official","path":"graph_judger/lora_infer.py","file_url":"https://github.com/hhy-huang/graphjudge/blob/HEAD/graph_judger/lora_infer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e96ec96db9ef37ba"}},{"code_sha256_prefix":"fa02d989f7ad994f","entry":"generate_prompt","repo":"hhy-huang/graphjudge","repo_kind":"official","path":"graph_judger/lora_infer_batch.py","file_url":"https://github.com/hhy-huang/graphjudge/blob/HEAD/graph_judger/lora_infer_batch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa02d989f7ad994f"}},{"code_sha256_prefix":"6f1e024958dca36b","entry":"get_chatgpt_completion","repo":"hhy-huang/graphjudge","repo_kind":"official","path":"chat/run_chatgpt_gj.py","file_url":"https://github.com/hhy-huang/graphjudge/blob/HEAD/chat/run_chatgpt_gj.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f1e024958dca36b"}},{"code_sha256_prefix":"d47506b71865ea46","entry":"process_input","repo":"hhy-huang/graphjudge","repo_kind":"official","path":"graph_judger/bert_classifier_infer.py","file_url":"https://github.com/hhy-huang/graphjudge/blob/HEAD/graph_judger/bert_classifier_infer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d47506b71865ea46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}