{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T14:02:30Z","timestamp":1789912950606,"version":"4.0.1"},"reference-count":35,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Eval Rev"],"abstract":"<jats:p>Document-level relation extraction must identify relations when entity mentions and supporting evidence are distributed across multiple sentences. Existing methods often use entity representations that remain fixed after encoding and provide limited support for progressively retrieving and combining dispersed evidence. This study improves complex cross-sentence relation reasoning by allowing entity representations to evolve during inference and by retrieving evidence from both entities in a target pair. The proposed multilayer iterative framework combines the Dynamic Entity Representation Mechanism (DERM) and Dual-Perspective Query Mechanism (DPQM). DERM propagates and updates entity states across reasoning layers using document context. DPQM retrieves evidence separately from head- and tail-entity perspectives and adaptively fuses the resulting representations. The framework was evaluated on Re-DocRED using BERT-base with Adaptive Thresholding and Localized cOntext Pooling (ATLOP) and DocuNet as backbones. Evaluations included overall F1, Ign F1, inter-sentence F1, evidence-based recall, ablation studies, and computational cost analysis. With ATLOP, the proposed method achieved 76.42% F1 and 75.22% Ign F1, exceeding the baseline by 2.72 and 2.46 percentage points, respectively. Inter-sentence F1 increased by 3.74 percentage points. For relations supported by three or more evidence sentences, recall improved from 54.65% to 66.40%. In ablation results, DERM and DPQM provided complementary improvements, with DERM making the larger contribution in complex cases. Explicit entity-state propagation and evidence retrieval from both entity perspectives improved dispersed evidence integration in long documents. The largest gains occurred in cross-sentence relations and instances requiring multiple supporting evidence sentences; however, stronger evidence constraints and calibration are required to reduce unsupported predictions.<\/jats:p>","DOI":"10.1177\/0193841x261491411","type":"journal-article","created":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T03:36:05Z","timestamp":1789788965000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Performance Analysis of Dynamic Entity Representation and Dual-Perspective Query Mechanisms for Document-Level Relation Extraction"],"prefix":"10.1177","author":[{"given":"Yi","family":"Zhang","sequence":"first","affiliation":[{"name":"Nanjing Audit University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4219-6264","authenticated-orcid":false,"given":"Xiuqi","family":"Ruan","sequence":"additional","affiliation":[{"name":"Nanjing Audit University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1290-2884","authenticated-orcid":false,"given":"Xinbin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaotian","family":"Dong","sequence":"additional","affiliation":[{"name":"Nanjing Audit University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinle","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing Audit University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"e_1_3_3_2_1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown T. B.","year":"2020","unstructured":"Brown T. B., Mann B., Ryder N., Subbiah M., Kaplan J., Dhariwal P., Neelakantan A., Shyam P., Sastry G., Askell A., Agarwal S., Herbert-Voss A., Krueger G., Henighan T., Child R., Ramesh A., Ziegler D. M., Wu J., Winter C., Amodei D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877\u20131901. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_3_1","doi-asserted-by":"crossref","unstructured":"Christopoulou F. Miwa M. Ananiadou S. (2019). Connecting the dots: Document-level neural relation extraction with edge-oriented graphs. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing Hong Kong China 3-7 November 2019 (pp. 4925\u20134936). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D19-1498","DOI":"10.18653\/v1\/D19-1498"},{"key":"e_1_3_3_4_1","doi-asserted-by":"crossref","unstructured":"Devlin J. Chang M.-W. Lee K. Toutanova K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Hyatt Regency Minneapolis Minnesota USA 2\u20137 June 2019 (Vol. 1 pp. 4171\u20134186). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_3_5_1","doi-asserted-by":"crossref","unstructured":"Ethayarajh K. (2019). How contextual are contextualized word representations? Comparing the geometry of BERT ELMo and GPT-2 embeddings. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing Hong Kong China 3-7 November 2019 (pp. 55\u201365). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D19-1006","DOI":"10.18653\/v1\/D19-1006"},{"key":"e_1_3_3_6_1","doi-asserted-by":"crossref","unstructured":"Guo Q. Zhang J. Wang S. Tian L. Kang Z. Yan B. Xiao W. (2025). Bridging generative and discriminative learning: Few-shot relation extraction via two-stage knowledge-guided pre-training. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence Montreal Canada 16-22 August 2025 (pp. 8068\u20138076). International Joint Conferences on Artificial Intelligence Organization. https:\/\/doi.org\/10.24963\/ijcai.2025\/897","DOI":"10.24963\/ijcai.2025\/897"},{"key":"e_1_3_3_7_1","unstructured":"Jiang F. Niu J. Mo S. Fan S. (2022). Key mention pairs guided document-level relation extraction. In Proceedings of the 29th International Conference on Computational Linguistics Gyeongju Republic of Korea 12\u201317 October 2022 (pp. 1904\u20131914). International Committee on Computational Linguistics. https:\/\/aclanthology.org\/2022.coling-1.165\/"},{"key":"e_1_3_3_8_1","doi-asserted-by":"crossref","unstructured":"Li J. (2025). Hyperbolic graph convolutional network relation extraction model combining dependency syntax and contrastive learning. International Journal of Computational Intelligence Systems 18 Article 18. https:\/\/doi.org\/10.1007\/s44196-025-00738-2","DOI":"10.1007\/s44196-025-00738-2"},{"key":"e_1_3_3_9_1","doi-asserted-by":"crossref","unstructured":"Li J. Jia Z. Zheng Z. (2023). Semi-automatic data enhancement for document-level relation extraction with distant supervision from large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural LANGUAGE Processing Singapore 2023 (pp. 5495\u20135505). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.334","DOI":"10.18653\/v1\/2023.emnlp-main.334"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2026.3668580"},{"key":"e_1_3_3_11_1","doi-asserted-by":"crossref","unstructured":"Ma Y. Wang A. Okazaki N. (2023). DREEAM: Guiding attention with evidence for improving document-level relation extraction. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational linguistics Dubrovnik Croatia 2\u20136 May 2023 (pp. 1971\u20131983). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.eacl-main.145","DOI":"10.18653\/v1\/2023.eacl-main.145"},{"key":"e_1_3_3_12_1","doi-asserted-by":"crossref","unstructured":"Nan G. Guo Z. Sekulic I. Lu W. (2020). Reasoning with latent structure refinement for document-level relation extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 1546\u20131557). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.141","DOI":"10.18653\/v1\/2020.acl-main.141"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00049"},{"key":"e_1_3_3_14_1","doi-asserted-by":"crossref","unstructured":"Ru D. Sun C. Feng J. Qiu L. Zhou H. Zhang W. Yu Y. Li L. (2021). Learning logic rules for document-level relation extraction. In Proceedings of the 2021 Conference on Empirical Methods in natural Language Processing Punta Cana Dominican Republic 7\u201311 November 2021 (pp. 1239\u20131250). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.95","DOI":"10.18653\/v1\/2021.emnlp-main.95"},{"key":"e_1_3_3_15_1","doi-asserted-by":"crossref","unstructured":"Sun P. Zhang R. Jiang Y. Kong T. Xu C. Zhan W. Tomizuka M. Li L. Yuan Z. Wang C. Luo P. (2021). Sparse R-CNN: End-to-end object detection with learnable proposals. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Virtual 20-25 June 2021 (pp. 14454\u201314463). IEEE. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01422","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.132"},{"key":"e_1_3_3_17_1","doi-asserted-by":"crossref","unstructured":"Tan Q. Xu L. Bing L. Ng H. T. Aljunied S. M. (2022b). Revisiting DocRED: Addressing the false negative problem in relation extraction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing Abu Dhabi United Arab Emirates 7\u201311 December 2022 (pp. 8472\u20138487). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.580","DOI":"10.18653\/v1\/2022.emnlp-main.580"},{"key":"e_1_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47426-3_16"},{"key":"e_1_3_3_19_1","volume-title":"LLaMA: Open and efficient foundation language models [Preprint]","author":"Touvron H.","year":"2023","unstructured":"Touvron H., Lavril T., Izacard G., Martinet X., Lachaux M.-A., Lacroix T., Rozi\u00e8re B., Goyal N., Hambro E., Azhar F., Rodriguez A., Joulin A., Grave E., Lample G. (2023). LLaMA: Open and efficient foundation language models [Preprint]. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2302.13971"},{"key":"e_1_3_3_20_1","doi-asserted-by":"crossref","unstructured":"Verga P. Strubell E. McCallum A. (2018). Simultaneously self-attending to all mentions for full-abstract biological relation extraction. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies New Orleans Louisiana 1\u20136 June 2018 (Vol. 1 pp. 872\u2013884). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/N18-1080","DOI":"10.18653\/v1\/N18-1080"},{"key":"e_1_3_3_21_1","doi-asserted-by":"crossref","unstructured":"Wadhwa S. Amir S. Wallace B. C. (2023). Revisiting relation extraction in the era of large language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics Toronto Canada 9\u201314 July 2023 (Vol. 1 pp. 15566\u201315589). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.868","DOI":"10.18653\/v1\/2023.acl-long.868"},{"key":"e_1_3_3_22_1","doi-asserted-by":"crossref","unstructured":"Wang D. Hu W. Cao E. Sun W. (2020). Global-to-local neural networks for document-level relation extraction. In Proceedings of the 2020 Conference on Empirical Methods in natural Language Processing Online 16\u201320 November 2020 (pp. 3711\u20133721). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.303","DOI":"10.18653\/v1\/2020.emnlp-main.303"},{"key":"e_1_3_3_23_1","doi-asserted-by":"crossref","unstructured":"Wang S. Sun X. Li X. Ouyang R. Wu F. Zhang T. Li J. Wang G. Guo C. (2025). GPT-NER: Named entity recognition via large language models. In Findings of the Association for Computational Linguistics: NAACL 2025 Albuquerque New Mexico USA 29 April-4 May 2025 (pp. 4257\u20134275). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2025.findings-naacl.239","DOI":"10.18653\/v1\/2025.findings-naacl.239"},{"key":"e_1_3_3_24_1","doi-asserted-by":"crossref","unstructured":"Xie Y. Shen J. Li S. Mao Y. Han J. (2022). Eider: Empowering document-level relation extraction with efficient evidence extraction and inference-stage fusion. In Findings of the Association for Computational Linguistics: ACL 2022 Dublin Ireland 2022 (pp. 257\u2013268). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.23","DOI":"10.18653\/v1\/2022.findings-acl.23"},{"key":"e_1_3_3_25_1","unstructured":"Xu X. Zhou Y. Xiang H. Li X. Zhang X. Qi L. Dou W. (2025). DocKS-RAG: Optimizing document-level relation extraction through LLM-enhanced hybrid prompt tuning. In Proceedings of the 42nd International Conference on Machine Learning Vancouver Convention Center Vancouver Canada 13\u201319 July 2025 (Vol. 267 pp. 69936\u201369949). PMLR. https:\/\/proceedings.mlr.press\/v267\/xu25am.html"},{"key":"e_1_3_3_26_1","doi-asserted-by":"crossref","unstructured":"Xue L. Zhang D. Dong Y. Tang J. (2024). AutoRE: Document-level relation extraction with large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics Bangkok Thailand 11\u201316 August 2024 (Vol. 3 pp. 211\u2013220). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2024.acl-demos.20","DOI":"10.18653\/v1\/2024.acl-demos.20"},{"key":"e_1_3_3_27_1","doi-asserted-by":"crossref","unstructured":"Yao Y. Ye D. Li P. Han X. Lin Y. Liu Z. Liu Z. Huang L. Zhou J. Sun M. (2019). DocRED: A large-scale document-level relation extraction dataset. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics Florence Italy 28 July-2 August 2019 (pp. 764\u2013777). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/P19-1074","DOI":"10.18653\/v1\/P19-1074"},{"key":"e_1_3_3_28_1","doi-asserted-by":"crossref","unstructured":"Ye D. Lin Y. Li P. Sun M. (2022). Packed levitated marker for entity and relation extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics Dublin Ireland 22-27 May 2022 (Vol. 1 pp. 4904\u20134917). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.337","DOI":"10.18653\/v1\/2022.acl-long.337"},{"key":"e_1_3_3_29_1","doi-asserted-by":"crossref","unstructured":"Yu M. Yin W. Hasan K. S. dos Santos C. Xiang B. Zhou B. (2017). Improved neural relation detection for knowledge base question answering. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics Vancouver Canada 30 July-4 Auguest 2017 (Vol. 1 pp. 571\u2013581). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/P17-1053","DOI":"10.18653\/v1\/P17-1053"},{"key":"e_1_3_3_30_1","doi-asserted-by":"crossref","unstructured":"Zeng D. Liu K. Chen Y. Zhao J. (2015). Distant supervision for relation extraction via piecewise convolutional neural networks. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing Lisbon Portugal 17\u201321 September 2015 (pp. 1753\u20131762). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/D15-1203","DOI":"10.18653\/v1\/D15-1203"},{"key":"e_1_3_3_31_1","doi-asserted-by":"crossref","unstructured":"Zeng S. Wu Y. Chang B. (2021). SIRE: Separate intra- and inter-sentential reasoning for document-level relation extraction. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 Online 1-6 August 2021 Association for Computational Linguistics (pp. 524\u2013534). https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.47","DOI":"10.18653\/v1\/2021.findings-acl.47"},{"key":"e_1_3_3_32_1","doi-asserted-by":"crossref","unstructured":"Zeng S. Xu R. Chang B Li L. (2020). Double graph based reasoning for document-level relation extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing Online 16\u201320 November 2020 (pp. 1630\u20131640). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.127","DOI":"10.18653\/v1\/2020.emnlp-main.127"},{"key":"e_1_3_3_33_1","doi-asserted-by":"crossref","unstructured":"Zhang F. Jin X. Cheng J. Yu H. Xu H. (2025a). Rethinking the role of LLMs for document-level relation extraction: A refiner with task distribution and probability fusion. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies Albuquerque New Mexico 29 April-4 May 2025 (Vol. 1 pp. 6293\u20136312). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2025.naacl-long.319","DOI":"10.18653\/v1\/2025.naacl-long.319"},{"key":"e_1_3_3_34_1","doi-asserted-by":"crossref","unstructured":"Zhang F. Yu H. Cheng J. Xu H. (2025b). Entity pair-guided relation summarization and retrieval in LLMs for document-level relation extraction. In Findings of the Association for Computational Linguistics: NAACL 2025 Albuquerque New Mexico April 2025 (pp. 4022\u20134037). Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2025.findings-naacl.224","DOI":"10.18653\/v1\/2025.findings-naacl.224"},{"key":"e_1_3_3_35_1","doi-asserted-by":"crossref","unstructured":"Zhang N. Chen X. Xie X. Deng S. Tan C. Chen M. Huang F. Si L. Chen H. (2021). Document-level relation extraction as semantic segmentation. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence Montreal Canada 19\u201327 August 2021 (pp. 3999\u20134006). International Joint Conferences on Artificial Intelligence Organization. https:\/\/doi.org\/10.24963\/ijcai.2021\/551","DOI":"10.24963\/ijcai.2021\/551"},{"key":"e_1_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17717"}],"container-title":["Evaluation Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0193841X261491411","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/0193841X261491411","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/0193841X261491411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T13:18:17Z","timestamp":1789910297000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/0193841X261491411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":35,"alternative-id":["10.1177\/0193841X261491411"],"URL":"https:\/\/doi.org\/10.1177\/0193841x261491411","relation":{},"ISSN":["0193-841X","1552-3926"],"issn-type":[{"value":"0193-841X","type":"print"},{"value":"1552-3926","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]},"article-number":"0193841X261491411"}}