pith. sign in

arxiv: 2606.26986 · v1 · pith:OMZXC6DJnew · submitted 2026-06-25 · 💻 cs.CL · cs.AI

ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models

Xin Lin , Liang Zhang , Guoqi Ma , Hongyao Tu , Jinsong Su This is my paper

Pith reviewed 2026-06-26 05:03 UTC · model grok-4.3

classification 💻 cs.CL cs.AI
keywords open relation extractionreasoning-guided extractionrelation filteringrelation predictioncoarse-to-fine reasoningunseen relationscomparative reasoninglarge reasoning models
0
0 comments X

The pith

ReaORE extracts unseen relations more reliably by filtering candidates with multi-aspect reasoning then distinguishing them via comparative reasoning.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes ReaORE as a framework that performs open relation extraction through a coarse-to-fine reasoning process using large reasoning models. It first filters an initial set of relations by reasoning over multiple aspects of the input and supplementing with embedding similarity to ensure the target is present, then predicts the correct relation by applying fine-grained comparative reasoning to separate easily confused options. This setup is meant to overcome the label-free nature of clustering approaches and the weak discrimination of direct large language model generation. A sympathetic reader would care because more dependable extraction of novel relations from text supports downstream tasks like automated knowledge base population.

Core claim

ReaORE performs relation extraction through coarse-to-fine relation reasoning consisting of relation filtering, which reasons over multiple aspects to understand relations and instances, yielding an initial relation set, and further supplements and filters relations via embedding-based similarity to ensure the target relation is included, followed by relation prediction, which aims to predict the target relations from the above set via fine-grained comparative reasoning to better distinguish easily confused relations.

What carries the argument

The two-stage coarse-to-fine reasoning process: relation filtering via multi-aspect reasoning plus embedding similarity, followed by relation prediction via fine-grained comparative reasoning.

If this is right

  • Generates explicit labels for unseen relation types unlike clustering methods.
  • Achieves stronger discrimination among easily confused relations than direct generation approaches.
  • Outperforms existing baselines on two widely used OpenRE datasets.
  • Supports more reliable generalization to novel relations in unstructured text.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The embedding similarity supplement in the filtering stage may be what prevents reasoning errors from dropping the correct relation.
  • The same progressive filtering-plus-comparison pattern could transfer to other NLP tasks that require separating similar categories.
  • Gains may scale with the underlying reasoning model's capability, suggesting tests with newer or larger models.
  • The method's reliance on both reasoning and embeddings invites experiments that isolate each component's contribution.

Load-bearing premise

Large reasoning models can consistently produce reliable multi-aspect reasoning and comparative reasoning outputs that correctly include the target relation in the filtered set and distinguish easily confused relations without systematic errors or hallucinations.

What would settle it

A held-out test set or error analysis showing that the filtering stage frequently excludes the correct target relation or the prediction stage systematically mislabels pairs of similar relations on the standard OpenRE benchmarks.

Figures

Figures reproduced from arXiv: 2606.26986 by Guoqi Ma, Hongyao Tu, Jinsong Su, Liang Zhang, Xin Lin.

Figure 1
Figure 1. Figure 1: Comparison of open relation extraction meth [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of ReaORE Framework. ReaORE follows a coarse-to-fine process: it first filters unseen [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Examples of the structured reasoning records produced by ReaORE. (a) The matching-based reasoning [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Performance comparison on FewRel and TA [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
read the original abstract

Open Relation Extraction (OpenRE) requires a model to extract unseen relations between head and tail entities from unstructured text for real-world applications. The core challenge of OpenRE lies in achieving reliable generalization to unseen relation types. Current OpenRE approaches either employ clustering techniques, which cannot generate relation labels and suffer from poor generalization, or rely on direct relation label generation via Large Language Models (LLMs), which lack sufficient discriminative capacity to distinguish easily confused relations. To address these limitations, we propose Reasoning-guided progressive OpenRE (ReaORE), a framework for performing relation extraction through coarse-to-fine relation reasoning. Specifically, ReaORE consists of two key stages: (i) relation filtering, which reasons over multiple aspects to understand relations and instances, yielding an initial relation set, and further supplements and filters relations via embedding-based similarity to ensure the target relation is included; (ii) relation prediction, which aims to predict the target relations from the above set via fine-grained comparative reasoning to better distinguish easily confused relations. Extensive experiments on two widely used OpenRE datasets demonstrate that ReaORE outperforms existing baselines.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The manuscript proposes ReaORE, a framework for open relation extraction (OpenRE) that performs coarse-to-fine reasoning with large reasoning models. It consists of a relation filtering stage that applies multi-aspect reasoning over relations and instances followed by embedding-based similarity filtering to produce an initial candidate set, and a relation prediction stage that applies fine-grained comparative reasoning to select the target relation from that set. The central claim is that this progressive structure outperforms existing baselines on two widely used OpenRE datasets by improving generalization to unseen relations and discrimination among confused ones.

Significance. If the experimental claims hold after proper validation, the work would be significant for OpenRE because it directly targets the discriminative weakness of direct LLM label generation and the label-less limitation of clustering methods. The explicit use of multi-aspect and comparative reasoning stages offers a concrete mechanism for leveraging LRMs that could generalize beyond the two datasets tested.

major comments (3)
  1. [Abstract, §4] Abstract and §4 (Experiments): the outperformance claim is stated without any reported metrics, baselines, dataset statistics, or error analysis, so the central empirical claim cannot be evaluated from the manuscript as written.
  2. [§3.1] §3.1 (Relation Filtering): no quantitative results (e.g., recall of the target relation in the filtered set) or failure-case analysis are supplied for the multi-aspect reasoning plus embedding step; this is load-bearing because the subsequent prediction stage can only succeed if the target is retained.
  3. [§3.2] §3.2 (Relation Prediction): no ablation or comparative-reasoning quality metrics are given to show that the fine-grained stage actually improves distinction of easily confused relations over a single-pass LLM prompt; without this, gains could be attributable to generic LLM prompting rather than the proposed coarse-to-fine structure.
minor comments (2)
  1. [§3.1] The description of embedding similarity in filtering lacks the exact similarity function and threshold selection procedure.
  2. [§3] Prompt templates or example reasoning traces for both stages are not provided, hindering reproducibility.

Simulated Author's Rebuttal

3 responses · 0 unresolved

Thank you for the referee's constructive comments. We agree that the manuscript as submitted lacks the quantitative details needed to substantiate the central claims. We will revise the abstract, Sections 3 and 4 to incorporate the requested metrics, ablations, and analyses. Point-by-point responses follow.

read point-by-point responses

  1. Referee: [Abstract, §4] Abstract and §4 (Experiments): the outperformance claim is stated without any reported metrics, baselines, dataset statistics, or error analysis, so the central empirical claim cannot be evaluated from the manuscript as written.

    Authors: We agree that the abstract and experimental section do not contain specific numbers, making evaluation difficult. In the revision we will update the abstract with key F1 scores on the two datasets, explicitly list all baselines, add dataset statistics, and expand Section 4 with an error analysis. revision: yes

  2. Referee: [§3.1] §3.1 (Relation Filtering): no quantitative results (e.g., recall of the target relation in the filtered set) or failure-case analysis are supplied for the multi-aspect reasoning plus embedding step; this is load-bearing because the subsequent prediction stage can only succeed if the target is retained.

    Authors: We concur that quantitative validation of the filtering stage is essential. The revised manuscript will report recall of the target relation in the filtered candidate set and include failure-case analysis for the multi-aspect reasoning and embedding-based filtering steps. revision: yes

  3. Referee: [§3.2] §3.2 (Relation Prediction): no ablation or comparative-reasoning quality metrics are given to show that the fine-grained stage actually improves distinction of easily confused relations over a single-pass LLM prompt; without this, gains could be attributable to generic LLM prompting rather than the proposed coarse-to-fine structure.

    Authors: We recognize the need to isolate the benefit of comparative reasoning. The revision will add ablation studies contrasting the full pipeline against a single-pass LLM baseline and will include metrics assessing the quality of the fine-grained stage on confused relations. revision: yes

Circularity Check

0 steps flagged

No circularity in derivation chain

full rationale

The paper describes a procedural framework (ReaORE) consisting of two stages—relation filtering via multi-aspect reasoning plus embedding similarity, followed by comparative reasoning for prediction—without any equations, fitted parameters, or mathematical derivations. The claimed outperformance rests on experimental results on standard datasets rather than any self-referential reduction or self-citation chain that would make the method equivalent to its inputs by construction. No load-bearing steps match the enumerated circularity patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract provides no equations, parameters, or explicit assumptions to populate the ledger.

pith-pipeline@v0.9.1-grok · 5732 in / 1066 out tokens · 31596 ms · 2026-06-26T05:03:25.630239+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

62 extracted references · 6 canonical work pages

  1. [1]

    Artificial Intelligence Review , volume=

    A survey on cutting-edge relation extraction techniques based on language models , author=. Artificial Intelligence Review , volume=. 2025 , publisher=

    2025

  2. [2]

    Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies , pages=

    Knowledge base population: Successful approaches and challenges , author=. Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies , pages=

  3. [3]

    Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

    Improved neural relation detection for knowledge base question answering , author=. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

  4. [4]

    Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

    Actively supervised clustering for open relation extraction , author=. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

  5. [5]

    Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

    LLM-OREF: An Open Relation Extraction Framework Based on Large Language Models , author=. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

    2025

  6. [6]

    Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=

    SelfORE: Self-supervised relational feature learning for open relation extraction , author=. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=

    2020

  7. [7]

    Proceedings of the 2021 conference on empirical methods in natural language processing , pages=

    A relation-oriented clustering method for open relation extraction , author=. Proceedings of the 2021 conference on empirical methods in natural language processing , pages=

    2021

  8. [8]

    Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

    Towards a more generalized approach in open relation extraction , author=. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

  9. [9]

    Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

    Deepresearcher: Scaling deep research via reinforcement learning in real-world environments , author=. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

    2025

  10. [10]

    Frontiers of Computer Science , volume=

    Large language models for generative information extraction: A survey , author=. Frontiers of Computer Science , volume=. 2024 , publisher=

    2024

  11. [11]

    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

    When phrases meet probabilities: Enabling open relation extraction with cooperating large language models , author=. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

  12. [13]

    Transactions of the Association for Computational Linguistics , volume=

    Lost in the Middle: How Language Models Use Long Contexts , author=. Transactions of the Association for Computational Linguistics , volume=. 2024 , doi=

    2024

  13. [14]

    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

    Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training , author=. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=. 2024 , doi=

    2024

  14. [15]

    Nature , volume=

    DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning , author=. Nature , volume=. 2025 , publisher=

    2025

  15. [17]

    Qwq: Reflect deeply on the boundaries of the unknown , author=

  16. [19]

    Academic Emergency Medicine , volume=

    Diagnostic reasoning and cognitive error in emergency medicine: Implications for teaching and learning , author=. Academic Emergency Medicine , volume=. 2025 , publisher=

    2025

  17. [21]

    Aho and Jeffrey D

    Alfred V. Aho and Jeffrey D. Ullman , title =. 1972

    1972

  18. [22]

    Publications Manual , year = "1983", publisher =

    1983

  19. [23]

    Chandra and Dexter C

    Ashok K. Chandra and Dexter C. Kozen and Larry J. Stockmeyer , year = "1981", title =. doi:10.1145/322234.322243

    work page doi:10.1145/322234.322243 1981

  20. [24]

    Scalable training of

    Andrew, Galen and Gao, Jianfeng , booktitle=. Scalable training of

  21. [25]

    Dan Gusfield , title =. 1997

    1997

  22. [26]

    Tetreault , title =

    Mohammad Sadegh Rasooli and Joel R. Tetreault , title =. Computing Research Repository , volume =. 2015 , url =

    2015

  23. [27]

    A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =

    Ando, Rie Kubota and Zhang, Tong , Issn =. A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =. Journal of Machine Learning Research , Month = dec, Numpages =

  24. [28]

    Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing , pages=

    FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation , author=. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing , pages=

    2018

  25. [29]

    Conference on empirical methods in natural language processing , year=

    Position-aware attention and supervised data improve slot filling , author=. Conference on empirical methods in natural language processing , year=

  26. [30]

    The first international conference on language resources and evaluation workshop on linguistics coreference , volume=

    Algorithms for scoring coreference chains , author=. The first international conference on language resources and evaluation workshop on linguistics coreference , volume=. 1998 , organization=

    1998

  27. [31]

    V-Measure: A Conditional Entropy-Based External Cluster Evaluation Measure , journal=

    Rosenberg, Andrew and Hirschberg, Julia , year=. V-Measure: A Conditional Entropy-Based External Cluster Evaluation Measure , journal=

  28. [32]

    Journal of classification , volume=

    Comparing partitions , author=. Journal of classification , volume=. 1985 , publisher=

    1985

  29. [36]

    2021 , eprint=

    LoRA: Low-Rank Adaptation of Large Language Models , author=. 2021 , eprint=

    2021

  30. [37]

    2019 , eprint=

    Decoupled Weight Decay Regularization , author=. 2019 , eprint=

    2019

  31. [38]

    2023 , eprint=

    Efficient Memory Management for Large Language Model Serving with PagedAttention , author=. 2023 , eprint=

    2023

  32. [39]

    S elf ORE : Self-supervised Relational Feature Learning for Open Relation Extraction

    Hu, Xuming and Wen, Lijie and Xu, Yusong and Zhang, Chenwei and Yu, Philip. S elf ORE : Self-supervised Relational Feature Learning for Open Relation Extraction. EMNLP 2020. 2020. doi:10.18653/v1/2020.emnlp-main.299

    work page doi:10.18653/v1/2020.emnlp-main.299 2020

  33. [40]

    Actively Supervised Clustering for Open Relation Extraction

    Zhao, Jun and Zhang, Yongxin and Zhang, Qi and Gui, Tao and Wei, Zhongyu and Peng, Minlong and Sun, Mingming. Actively Supervised Clustering for Open Relation Extraction. ACL 2023. 2023. doi:10.18653/v1/2023.acl-long.273

    work page doi:10.18653/v1/2023.acl-long.273 2023

  34. [41]

    Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In The first international conference on language resources and evaluation workshop on linguistics coreference, volume 1, pages 563--566. Citeseer

    1998

  35. [42]

    Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216, 4(5)

    Pith/arXiv arXiv 2024

  36. [43]

    Jose A Diaz-Garcia and Julio Amador Diaz Lopez. 2025. A survey on cutting-edge relation extraction techniques based on language models. Artificial Intelligence Review, 58(9):287

    2025

  37. [44]

    Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, and 1 others. 2025. Deepseek-r1 incentivizes reasoning in llms through reinforcement learning. Nature, 645(8081):633--638

    2025

  38. [45]

    Xu Han, Hao Zhu, Pengfei Yu, Ziyun Wang, Yuan Yao, Zhiyuan Liu, and Maosong Sun. 2018. Fewrel: A large-scale supervised few-shot relation classification dataset with state-of-the-art evaluation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4803--4809

    2018

  39. [46]

    Junqing He, Kunhao Pan, Xiaoqun Dong, Zhuoyang Song, Yibo Liu, Qianguo Sun, Yuxin Liang, Hao Wang, Enming Zhang, and Jiaxing Zhang. 2024. https://doi.org/10.18653/v1/2024.acl-long.736 Never lost in the middle: Mastering long-context question answering with position-agnostic decompositional training . In Proceedings of the 62nd Annual Meeting of the Associ...

    work page doi:10.18653/v1/2024.acl-long.736 2024

  40. [47]

    Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

    Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. https://arxiv.org/abs/2106.09685 Lora: Low-rank adaptation of large language models . Preprint, arXiv:2106.09685

    Pith/arXiv arXiv 2021

  41. [48]

    Xuming Hu, Lijie Wen, Yusong Xu, Chenwei Zhang, and Philip S Yu. 2020. Selfore: Self-supervised relational feature learning for open relation extraction. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3673--3682

    2020

  42. [49]

    Kaixuan Huang, Jiacheng Guo, Zihao Li, Xiang Ji, Jiawei Ge, Wenzhe Li, Yingqing Guo, Tianle Cai, Hui Yuan, Runzhe Wang, and 1 others. 2025. Math-perturb: Benchmarking llms' math reasoning abilities against hard perturbations. arXiv preprint arXiv:2502.06453

    arXiv 2025

  43. [50]

    Lawrence Hubert and Phipps Arabie. 1985. Comparing partitions. Journal of classification, 2:193--218

    1985

  44. [51]

    Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, and 1 others. 2024. Openai o1 system card. arXiv preprint arXiv:2412.16720

    Pith/arXiv arXiv 2024

  45. [52]

    Heng Ji and Ralph Grishman. 2011. Knowledge base population: Successful approaches and challenges. In Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies, pages 1148--1158

    2011

  46. [53]

    Gonzalez, Hao Zhang, and Ion Stoica

    Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. https://arxiv.org/abs/2309.06180 Efficient memory management for large language model serving with pagedattention . Preprint, arXiv:2309.06180

    Pith/arXiv arXiv 2023

  47. [54]

    Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang

    Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. https://doi.org/10.1162/tacl_a_00638 Lost in the middle: How language models use long contexts . Transactions of the Association for Computational Linguistics, 12:157--173

    work page doi:10.1162/tacl_a_00638 2024

  48. [55]

    Juri Opitz and Sebastian Burst. 2019. Macro f1 and macro f1. arXiv preprint arXiv:1911.03347

    arXiv 2019

  49. [56]

    Thierry Pelaccia, Jonathan Sherbino, Peter Wyer, and Geoff Norman. 2025. Diagnostic reasoning and cognitive error in emergency medicine: Implications for teaching and learning. Academic Emergency Medicine, 32(3):320--326

    2025

  50. [57]

    Andrew Rosenberg and Julia Hirschberg. 2007. V-measure: A conditional entropy-based external cluster evaluation measure. Empirical Methods in Natural Language Processing,Empirical Methods in Natural Language Processing

    2007

  51. [58]

    Qwen Team. 2024. Qwq: Reflect deeply on the boundaries of the unknown

    2024

  52. [59]

    Hongyao Tu, Liang Zhang, Yujie Lin, Xin Lin, Haibo Zhang, Long Zhang, and Jinsong Su. 2025. Llm-oref: An open relation extraction framework based on large language models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 9051--9063

    2025

  53. [60]

    Jiaxin Wang, Lingling Zhang, Wee Sun Lee, Yujie Zhong, Liwei Kang, and Jun Liu. 2024. When phrases meet probabilities: Enabling open relation extraction with cooperating large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13130--13147

    2024

  54. [61]

    Qing Wang, Yuepei Li, Qiao Qiao, Kang Zhou, and Qi Li. 2025 a . Towards a more generalized approach in open relation extraction. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6343--6354

    2025

  55. [62]

    Ziyue Wang, Junde Wu, Linghan Cai, Chang Han Low, Xihong Yang, Qiaxuan Li, and Yueming Jin. 2025 b . Medagent-pro: Towards evidence-based multi-modal medical diagnosis via reasoning agentic workflow. arXiv preprint arXiv:2503.18968

    arXiv 2025

  56. [63]

    Derong Xu, Wei Chen, Wenjun Peng, Chao Zhang, Tong Xu, Xiangyu Zhao, Xian Wu, Yefeng Zheng, Yang Wang, and Enhong Chen. 2024. Large language models for generative information extraction: A survey. Frontiers of Computer Science, 18(6):186357

    2024

  57. [64]

    An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388

    Pith/arXiv arXiv 2025

  58. [65]

    Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cicero Dos Santos, Bing Xiang, and Bowen Zhou. 2017. Improved neural relation detection for knowledge base question answering. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 571--581

    2017

  59. [66]

    Yuhao Zhang, Victor Zhong, Danqi Chen, Gabor Angeli, and Christopher D Manning. 2017. Position-aware attention and supervised data improve slot filling. In Conference on empirical methods in natural language processing

    2017

  60. [67]

    Jun Zhao, Tao Gui, Qi Zhang, and Yaqian Zhou. 2021. A relation-oriented clustering method for open relation extraction. In Proceedings of the 2021 conference on empirical methods in natural language processing, pages 9707--9718

    2021

  61. [68]

    Jun Zhao, Yongxin Zhang, Qi Zhang, Tao Gui, Zhongyu Wei, Minlong Peng, and Mingming Sun. 2023. Actively supervised clustering for open relation extraction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4985--4997

    2023

  62. [69]

    Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, and Zheyan Luo. 2024. https://doi.org/10.18653/v1/2024.acl-demos.38 L lama F actory: Unified efficient fine-tuning of 100+ language models . In ACL 2024

    work page doi:10.18653/v1/2024.acl-demos.38 2024