{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:33:06Z","timestamp":1760059986307,"version":"build-2065373602"},"reference-count":28,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T00:00:00Z","timestamp":1753660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CIPSC-SMP-Zhipu Large Model Cross-Disciplinary Fund","award":["13501050093","202404AP110047"],"award-info":[{"award-number":["13501050093","202404AP110047"]}]},{"name":"Doctoral Research Fund of Zhengzhou University of Light Industry","award":["13501050093","202404AP110047"],"award-info":[{"award-number":["13501050093","202404AP110047"]}]},{"name":"\u201cDouble Innovation\u201d Special Project-Yunnan Province Science and Technology Small and Medium-sized Enterprises (SMEs) Technology Innovation Fund Project","award":["13501050093","202404AP110047"],"award-info":[{"award-number":["13501050093","202404AP110047"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>To address issues commonly observed during the inference phase of large language models\u2014such as inconsistent labels, formatting errors, or semantic deviations\u2014a series of targeted strategies has been proposed. First, a relation label refinement strategy based on semantic similarity and syntactic structure has been designed to calibrate the model\u2019s outputs, thereby improving the accuracy and consistency of label prediction. Second, to meet the contextual modeling needs of different types of instance bags, a multi-level contextual augmentation strategy has been constructed. For multi-sentence instance bags, a graph-based retrieval enhancement mechanism is introduced, which integrates intra-bag entity co-occurrence networks with document-level sentence association graphs to strengthen the model\u2019s understanding of cross-sentence semantic relations. For single-sentence instance bags, a semantic expansion strategy based on term frequency-inverse document frequency is employed to retrieve similar sentences. This enriches the training context under the premise of semantic consistency, alleviating the problem of insufficient contextual information. Notably, the proposed multi-granularity framework captures semantic symmetry between entities and relations across different levels of context, which is crucial for accurate and balanced relation understanding. The proposed methodology offers practical advancements for semantic analysis applications, particularly in knowledge graph development.<\/jats:p>","DOI":"10.3390\/sym17081201","type":"journal-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T14:05:47Z","timestamp":1753711547000},"page":"1201","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Contextual Augmentation via Retrieval for Multi-Granularity Relation Extraction in LLMs"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2283-9089","authenticated-orcid":false,"given":"Danjie","family":"Han","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingzhong","family":"Meng","sequence":"additional","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhengzhou University of Light Industry, Zhengzhou 450001, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cunhan","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beijing Institute of Technology, Beijing 100081, China"},{"name":"Southeast Academy of Information Technology, Beijing Institute of Technology, Putian 351100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanghao","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beijing Institute of Technology, Beijing 100081, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changsen","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beijing Institute of Technology, Beijing 100081, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5639-5214","authenticated-orcid":false,"given":"Yuxi","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Software Chinese Academy of Sciences, Beijing 100190, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,28]]},"reference":[{"key":"ref_1","unstructured":"Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., and Wei, H. (2024). Qwen2.5 technical report. arXiv."},{"key":"ref_2","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., and Vaughan, A. (2024). The llama 3 herd of models. arXiv."},{"key":"ref_3","unstructured":"Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., Zhang, C., and Ruan, C. (2024). Deepseek-v3 technical report. arXiv."},{"key":"ref_4","first-page":"1","article-title":"Pre-trained language models for text generation: A survey","volume":"56","author":"Li","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s11280-024-01291-2","article-title":"A survey on large language models for recommendation","volume":"27","author":"Wu","year":"2024","journal-title":"World Wide Web"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3641850","article-title":"Codekgc: Code language model for generative knowledge graph construction","volume":"23","author":"Bi","year":"2024","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"ref_7","first-page":"413","article-title":"Large language models for automated q&a involving legal documents: A survey on algorithms, frameworks and applications","volume":"20","author":"Yang","year":"2024","journal-title":"Int. J. Web Inf. Syst."},{"key":"ref_8","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2\u20137). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Minneapolis, MN, USA."},{"key":"ref_9","unstructured":"Jat, S., Khandelwal, S., and Talukdar, P. (2018). Improving distantly supervised relation extraction using word and entity based attention. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hendrickx, I., Kim, S.N., Kozareva, Z., Nakov, P., S\u00e9aghdha, D.\u00d3., Pad\u00f3, S., Pennacchiotti, M., Romano, L., and Szpakowicz, S. (2010, January 15\u201316). SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations between Pairs of Nominals. Proceedings of the 5th International Workshop on Semantic Evaluation, Uppsala, Sweden.","DOI":"10.3115\/1621969.1621986"},{"key":"ref_11","unstructured":"Zhang, D., and Wang, D. (2015). Relation classification via recurrent neural network. arXiv."},{"key":"ref_12","unstructured":"Han, H., Wang, Y., Shomer, H., Guo, K., Ding, J., Lei, Y., Halappanavar, M., Rossi, R.A., Mukherjee, S., and Tang, X. (2024). Retrieval-augmented generation with graphs (graphrag). arXiv."},{"key":"ref_13","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., and Chen, W. (2022, January 25\u201329). LoRA: Low-Rank Adaptation of Large Language Models. Proceedings of the Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event."},{"key":"ref_14","unstructured":"Wei, X., Cui, X., Cheng, N., Wang, X., Zhang, X., Huang, S., Xie, P., Xu, J., Chen, Y., and Zhang, M. (2023). Zero-shot information extraction via chatting with chatgpt. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lou, J., Lu, Y., Dai, D., Jia, W., Lin, H., Han, X., Sun, L., and Wu, H. (2023, January 7\u201314). Universal information extraction as unified semantic matching. Proceedings of the AAAI conference on Artificial Intelligence, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i11.26563"},{"key":"ref_16","unstructured":"Han, R., Peng, T., Yang, C., Wang, B., Liu, L., and Wan, X. (2023). Is information extraction solved by chatgpt? An analysis of performance, evaluation criteria, robustness and errors. arXiv."},{"key":"ref_17","unstructured":"Li, B., Fang, G., Yang, Y., Wang, Q., Ye, W., Zhao, W., and Zhang, S. (2023). Evaluating ChatGPT\u2019s information extraction capabilities: An assessment of performance, explainability, calibration, and faithfulness. arXiv."},{"key":"ref_18","first-page":"15460","article-title":"Lasuie: Unifying information extraction with latent adaptive structure-aware generative language model","volume":"35","author":"Fei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"13491","DOI":"10.1007\/s00521-024-09728-5","article-title":"Diluie: Constructing diverse demonstrations of in-context learning with large language model for unified information extraction","volume":"36","author":"Guo","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_20","unstructured":"Wang, X., Zhou, W., Zu, C., Xia, H., Chen, T., Zhang, Y., Zheng, R., Ye, J., Zhang, Q., and Gui, T. (2023). Instructuie: Multi-task instruction tuning for unified information extraction. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Miao, X., Li, Y., Zhou, S., and Qian, T. (2024, January 11\u201316). Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction. Proceedings of the Findings of the Association for Computational Linguistics ACL 2024, Bangkok, Thailand.","DOI":"10.18653\/v1\/2024.findings-acl.146"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Xue, L., Zhang, D., Dong, Y., and Tang, J. (2024, January 11\u201316). AutoRE: Document-Level Relation Extraction with Large Language Models. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), Bangkok, Thailand.","DOI":"10.18653\/v1\/2024.acl-demos.20"},{"key":"ref_23","unstructured":"Efeoglu, S., and Paschke, A. (2024). Retrieval-augmented generation-based relation extraction. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"123478","DOI":"10.1016\/j.eswa.2024.123478","article-title":"GAP: A novel Generative context-Aware Prompt-tuning method for relation extraction","volume":"248","author":"Chen","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_25","unstructured":"Surdeanu, M., Tibshirani, J., Nallapati, R., and Manning, C.D. (2012, January 12\u201314). Multi-instance multi-label learning for relation extraction. Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Jeju, Republic of Korea."},{"key":"ref_26","unstructured":"Efeoglu, S., and Paschke, A. (2024). Relation extraction with fine-tuned large language models in retrieval augmented generation frameworks. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Angeli, G., Tibshirani, J., Wu, J., and Manning, C.D. (2014, January 25\u201329). Combining distant and partial supervision for relation extraction. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.","DOI":"10.3115\/v1\/D14-1164"},{"key":"ref_28","unstructured":"Shi, Z., and Luo, H. (2024). CRE-LLM: A domain-specific Chinese relation extraction framework with fine-tuned large language model. arXiv."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/8\/1201\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:17:14Z","timestamp":1760033834000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/8\/1201"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,28]]},"references-count":28,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["sym17081201"],"URL":"https:\/\/doi.org\/10.3390\/sym17081201","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,7,28]]}}}