pith. sign in

arxiv: 2606.28076 · v1 · pith:GQ2QAGR4new · submitted 2026-06-26 · 💻 cs.AI

Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering

Yongxue Shan , Meihan Wu , Cundi Fang , Jie Peng , Xiaodong Wang This is my paper

Pith reviewed 2026-06-29 04:02 UTC · model grok-4.3

classification 💻 cs.AI
keywords multi-hop KGQAontology graphevidence path inferencebidirectional retrievaliterative refinementknowledge graph question answeringtype constraints
0
0 comments X

The pith

A relation-centric ontology graph enables bidirectional retrieval that suppresses noisy mixed-type paths in multi-hop KGQA.

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

The paper introduces OPI to address the rapid growth of search spaces with noisy mixed-type paths and the failure of retrieved paths to meet semantic constraints in multi-hop knowledge graph question answering. It builds a relation-centric ontology graph that captures head-tail type constraints of relations as a compact interface for answer-side constraints. This supports a bidirectional retrieval mechanism that maps the predicted answer type to compatible final-hop relations and combines topic-side prefix expansion with answer-side matching. An iterative refinement strategy then reassesses paths and candidates under the question context to filter irrelevant evidence. Experiments demonstrate that these steps reduce the search space and yield performance gains on WebQSP, CWQ, and MetaQA.

Core claim

OPI introduces a relation-centric ontology graph to capture the head-tail type constraints of relations, providing a compact interface for answer-side constraints. Based on this ontology graph, OPI first introduces a bidirectional retrieval mechanism by mapping the predicted answer type to compatible final-hop relations and combining topic-side prefix expansion with answer-side final-hop matching, thereby suppressing noisy mixed-type expansion. OPI further adopts an iterative refinement strategy to reassess retrieved paths and candidate answers under the question context, filtering type-compatible but question-irrelevant evidence for more reliable answer prediction.

What carries the argument

The relation-centric ontology graph that encodes head-tail type constraints of relations, used to map answer types to final-hop relations for guided bidirectional retrieval.

If this is right

  • Suppresses noisy mixed-type expansion through answer-side final-hop matching.
  • Improves Hit@1/F1 by 4.6/5.0 points on WebQSP over strongest priors.
  • Improves Hit@1/F1 by 8.9/3.3 points on CWQ over strongest priors.
  • Achieves near-saturated Hit@1 on MetaQA using the retrieval module alone.

Where Pith is reading between the lines

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

  • The same type-constraint mechanism could be tested on single-hop KGQA to isolate its contribution to multi-hop cases.
  • If the ontology is learned from data rather than provided, the framework might extend to knowledge graphs without explicit type annotations.
  • The iterative refinement step suggests that question-context filtering can be layered on top of other retrieval methods that lack type guidance.

Load-bearing premise

The relation-centric ontology graph accurately encodes head-tail type constraints and that mapping a predicted answer type to final-hop relations will suppress noisy mixed-type expansion.

What would settle it

Running the method on a benchmark where the ontology graph's type mappings are deliberately altered or removed, checking whether performance drops below the strongest prior baselines on WebQSP or CWQ.

Figures

Figures reproduced from arXiv: 2606.28076 by Cundi Fang, Jie Peng, Meihan Wu, Xiaodong Wang, Yongxue Shan.

Figure 1
Figure 1. Figure 1: Illustration of two main challenges in multi-hop [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: An example of a knowledge graph and its ontology [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Overall inference pipeline of OPI. The left part shows ontology-guided bidirectional retrieval, which retrieves tail [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Efficiency and robustness analysis of OPI. (a)-(b) Search-space and retrieval-cost comparison between forward-only [PITH_FULL_IMAGE:figures/full_fig_p012_4.png] view at source ↗
read the original abstract

Knowledge graph question answering (KGQA) aims to answer natural-language questions by reasoning over structured facts. Existing multi-hop KGQA methods mainly rely on topic-centered expansion, which faces two key challenges: the search space rapidly grows with noisy mixed-type paths, and retrieved paths may fail to satisfy the semantic constraints of complex questions. To address these challenges, we propose OPI, an ontology-guided evidence path inference framework for multi-hop KGQA. OPI introduces a relation-centric ontology graph to capture the head-tail type constraints of relations, providing a compact interface for answer-side constraints. Based on this ontology graph, OPI first introduces a bidirectional retrieval mechanism by mapping the predicted answer type to compatible final-hop relations and combining topic-side prefix expansion with answer-side final-hop matching, thereby suppressing noisy mixed-type expansion. OPI further adopts an iterative refinement strategy to reassess retrieved paths and candidate answers under the question context, filtering type-compatible but question-irrelevant evidence for more reliable answer prediction. Experiments on WebQSP, CWQ, and MetaQA show that OPI substantially reduces the search space, improves Hit@1/F1 by 4.6/5.0 points on WebQSP and 8.9/3.3 points on CWQ over the strongest prior results, and achieves near-saturated Hit@1 on MetaQA with the retrieval module alone.

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

1 major / 1 minor

Summary. The manuscript presents OPI, an ontology-guided evidence path inference framework for multi-hop KGQA. It constructs a relation-centric ontology graph to encode head-tail type constraints of relations, enabling bidirectional retrieval (topic-side prefix expansion combined with answer-side final-hop matching via predicted answer types) to prune noisy mixed-type paths, followed by iterative refinement to filter contextually irrelevant evidence. Experiments on WebQSP, CWQ, and MetaQA report search-space reduction and gains of 4.6/5.0 Hit@1/F1 points on WebQSP and 8.9/3.3 on CWQ over prior results, plus near-saturated Hit@1 on MetaQA using retrieval alone.

Significance. If the ontology faithfully encodes KG constraints and the gains prove robust, the bidirectional mechanism offers a principled interface for answer-side semantic constraints that could improve both efficiency and reliability in multi-hop KGQA. The reported near-saturation on MetaQA with the retrieval module alone is a notable empirical strength.

major comments (1)
  1. [Section 3] Section 3 (Ontology Graph Construction and Bidirectional Retrieval): The relation-centric ontology graph is load-bearing for the claimed search-space reduction and performance gains, as it supplies the type-compatible final-hop relations used to suppress mixed-type expansion. No quantitative check (e.g., coverage, precision, or error rate of the encoded head-tail constraints against the KG for relations appearing in the test sets) is reported, leaving open whether the mechanism reliably prunes paths or whether gains could arise from the iterative refinement step alone.
minor comments (1)
  1. [Abstract] Abstract and §5 (Experiments): Performance deltas are stated without reference to the exact strongest baselines, without error bars, and without data-selection or random-seed details, which would strengthen reproducibility claims.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on the manuscript. Below we address the single major comment point by point.

read point-by-point responses

  1. Referee: [Section 3] Section 3 (Ontology Graph Construction and Bidirectional Retrieval): The relation-centric ontology graph is load-bearing for the claimed search-space reduction and performance gains, as it supplies the type-compatible final-hop relations used to suppress mixed-type expansion. No quantitative check (e.g., coverage, precision, or error rate of the encoded head-tail constraints against the KG for relations appearing in the test sets) is reported, leaving open whether the mechanism reliably prunes paths or whether gains could arise from the iterative refinement step alone.

    Authors: We agree that an explicit quantitative validation of the ontology graph would strengthen the claims. The relation-centric ontology graph is constructed by extracting every observed (head-type, relation, tail-type) triple directly from the full KG; therefore the encoded constraints match the KG exactly for every relation that appears in it. This yields 100% coverage and precision (zero error rate) by construction for all relations, including those in the test sets. While the original submission did not include a dedicated table or paragraph reporting these statistics, we will add one to Section 3 in the revision, listing the number of test-set relations, the number of unique head-tail type pairs per relation, and explicit confirmation of full coverage. The reported search-space reduction already isolates the effect of the ontology-guided final-hop matching; to further separate its contribution from iterative refinement we will also expand the ablation experiments accordingly. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected in claimed derivation.

full rationale

The paper's central contribution is an algorithmic framework (relation-centric ontology graph construction, bidirectional retrieval, iterative refinement) whose performance is measured by empirical gains on external benchmarks (WebQSP, CWQ, MetaQA) against prior methods. No equations, fitted parameters, or self-citations appear that reduce any prediction or uniqueness claim to a definitional identity or input by construction. The ontology is presented as an extracted interface from the KG for type constraints, and the reported improvements are treated as falsifiable experimental outcomes rather than tautological restatements of the method itself.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no free parameters, axioms, or invented entities are described.

pith-pipeline@v0.9.1-grok · 5785 in / 971 out tokens · 56664 ms · 2026-06-29T04:02:03.265342+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

58 extracted references · 11 canonical work pages · 1 internal anchor

  1. [1]

    Dhruv Agarwal, Rajarshi Das, Sopan Khosla, and Rashmi Gangadharaiah. 2024. Bring your own KG: Self-supervised program synthesis for zero-shot KGQA. In Findings of the association for computational linguistics: NAACL 2024. Association for Computational Linguistics, Mexico City, Mexico, 896–919

    2024

  2. [2]

    Hamed Babaei Giglou, Jennifer D’Souza, and Sören Auer. 2023. LLMs4OL: Large language models for ontology learning. InInternational Semantic Web Conference. Springer, 408–427

    2023

  3. [3]

    Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor

  4. [4]

    InProceedings of the 2008 ACM SIGMOD international conference on Management of data

    Freebase: a collaboratively created graph database for structuring human knowledge. InProceedings of the 2008 ACM SIGMOD international conference on Management of data. Association for Computing Machinery, Vancouver, BC, Canada, 1247–1250

    2008

  5. [5]

    Deyan Chen and Hong Zhao. 2018. Research on the method of extracting domain knowledge from the freebase RDF dumps.IEEE Access6 (2018), 50306–50322

    2018

  6. [6]

    2024.DeepSeek-V3 Technical Report

    DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. 2024.DeepSeek-V3 Technical Report. Technical Report arXiv:2412.19437. DeepSeek-AI. https://arxiv.org/abs/2412.19437

    Pith/arXiv arXiv 2024

  7. [7]

    Lianhong Ding, Na Ding, Qi Tao, and Peng Shi. 2025. Enhancing graph multi-hop reasoning for question answering with llms: An approach based on adaptive path generation.Journal of Intelligent Information Systems63, 5 (2025), 1455–1485

    2025

  8. [8]

    Xin Luna Dong. 2023. Generations of Knowledge Graphs: The Crazy Ideas and the Business Impact.Proc. VLDB Endow.16, 12 (Aug. 2023), 4130–4137. https://doi.org/10.14778/3611540.3611636

    work page doi:10.14778/3611540.3611636 2023

  9. [9]

    Giacomo Frisoni, Alessio Cocchieri, Alex Presepi, Gianluca Moro, and Zaiqiao Meng. 2024. To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question Answering. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Lun-Wei Ku, Andre Martins, and Vivek ...

    work page doi:10.18653/v1/2024.acl-long.533 2024

  10. [10]

    Maurice Funk, Simon Hosemann, Jean Christoph Jung, and Carsten Lutz. 2023. Towards ontology construction with language models. InJoint proceedings of the 1st workshop on Knowledge Base Construction from Pre-Trained Language Models (KBC-LM) and the 2nd challenge on Language Models for Knowledge Base Construction (LM-KBC) co-located with the 22nd Internatio...

    2023

  11. [11]

    Congcong Ge, Xiaoze Liu, Lu Chen, Yunjun Gao, and Baihua Zheng. 2021. LargeEA: aligning entities for large-scale knowledge graphs.Proceedings of the VLDB Endowment15, 2 (Oct. 2021), 237–245. https://doi.org/10.14778/3489496. 3489504

    work page doi:10.14778/3489496 2021

  12. [12]

    Gaole He, Yunshi Lan, Jing Jiang, Wayne Xin Zhao, and Ji-Rong Wen. 2021. Improving multi-hop knowledge base question answering by learning interme- diate supervision signals. InProceedings of the 14th ACM international conference on web search and data mining. Association for Computing Machinery, Online, 553–561

    2021

  13. [13]

    Yixin Ji, Kaixin Wu, Juntao Li, Wei Chen, Mingjie Zhong, Xu Jia, and Min Zhang

  14. [14]

    InFindings of the Associa- tion for Computational Linguistics: EMNLP 2024

    Retrieval and reasoning on KGs: Integrate knowledge graphs into large language models for complex question answering. InFindings of the Associa- tion for Computational Linguistics: EMNLP 2024. Association for Computational Linguistics, Miami, Florida, USA, 7598–7610

    2024

  15. [15]

    Jinhao Jiang, Kun Zhou, Zican Dong, Keming Ye, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Structgpt: A general framework for large language model to reason over structured data. InProceedings of the 2023 Conference on Empirical Meth- ods in Natural Language Processing. Association for Computational Linguistics, Singapore, 9237–9251

    2023

  16. [16]

    Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yaliang Li, and Ji-Rong Wen. 2023. Reasoninglm: Enabling structural subgraph reasoning in pre-trained language models for question answering over knowledge graph. InProceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Singapore, 3721–3735

    2023

  17. [17]

    Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, Yang Song, Chen Zhu, Hengshu Zhu, and Ji-Rong Wen. 2025. KG-Agent: An efficient autonomous agent framework for complex reasoning over knowledge graph. InProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Vienna, ...

    2025

  18. [18]

    Jinhao Jiang, Kun Zhou, Xin Zhao, and Ji-Rong Wen. 2023. UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowl- edge Graph. InThe Eleventh International Conference on Learning Representations. ICLR, OpenReview.net, Kigali, Rwanda, 16. https://openreview.net/forum?id= Z63RvyAZ2Vh

    2023

  19. [19]

    Longquan Jiang, Junbo Huang, Cedric Moller, and Ricardo Usbeck. 2025. Ontology-Guided, Hybrid Prompt Learning for Generalization in Knowledge Graph Question Answering. In2025 19th International Conference on Semantic Computing (ICSC). IEEE Computer Society, 28–35

    2025

  20. [20]

    Jiho Kim, Yeonsu Kwon, Yohan Jo, and Edward Choi. 2023. KG-GPT: A general framework for reasoning on knowledge graphs using large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics, Singapore, 9410–9421

    2023

  21. [21]

    Vamsi Krishna Kommineni, Birgitta König-Ries, and Sheeba Samuel. 2024. From human experts to machines: An LLM supported approach to ontology and knowl- edge graph construction.arXiv preprint arXiv:2403.08345(2024)

    arXiv 2024

  22. [22]

    Junlin Lee, Yequan Wang, Jing Li, and Min Zhang. 2024. Multimodal Reasoning with Multimodal Knowledge Graph. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, Bangkok, Thailand, 10767–10782. http...

    work page doi:10.18653/v1/2024 2024

  23. [23]

    Ben Liu, Jihai Zhang, Fangquan Lin, Cheng Yang, Min Peng, and Wotao Yin

  24. [24]

    InProceedings of the ACM on Web Conference

    Symagent: A neural-symbolic self-learning agent framework for complex reasoning over knowledge graphs. InProceedings of the ACM on Web Conference

  25. [25]

    Association for Computing Machinery, Sydney, Australia, 98–108

  26. [26]

    Runxuan Liu, Luobei Luobei, Jiaqi Li, Baoxin Wang, Ming Liu, Dayong Wu, Shijin Wang, and Bing Qin. 2025. Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answering. InProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Wanxiang Che, Joyce Nabende,...

    work page doi:10.18653/v1/2025.acl- 2025

  27. [27]

    Zhiqiang Liu, Chengtao Gan, Junjie Wang, Yichi Zhang, Zhongpu Bo, Mengshu Sun, Huajun Chen, and Wen Zhang. 2025. Ontotune: Ontology-driven self- training for aligning large language models. InProceedings of the ACM on Web Conference 2025. 119–133

    2025

  28. [28]

    Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2024. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. InThe Twelfth International Conference on Learning Representations. OpenReview.net, Vienna, Austria, 1–24. https://openreview.net/forum?id=ZGNWW7xZ6Q

    2024

  29. [29]

    Linhao Luo, Zicheng Zhao, Gholamreza Haffari, Yuan-Fang Li, Chen Gong, and Shirui Pan. 2025. Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models. InProceedings of the 42nd International Conference on Machine Learning, Vol. 267. Proceedings of Machine Learning Research, Vancouver, Canada, 41540–41565. https://proc...

    2025

  30. [30]

    Costas Mavromatis and George Karypis. 2025. Gnn-rag: Graph neural retrieval for efficient large language model reasoning on knowledge graphs. InFind- ings of the Association for Computational Linguistics: ACL 2025. Association for Computational Linguistics, Vienna, Austria, 16682–16699

    2025

  31. [31]

    Meta. 2024. Build the future of ai with meta llama 3. https://llama.meta.com/ llama3/

    2024

  32. [32]

    Microsoft. 2015. FastRDFStore-data. https://download.microsoft.com/download/ A/E/4/AE428B7A-9EF9-446C-85CF-D8ED0C9B1F26/FastRDFStore-data.zip

    2015

  33. [33]

    Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly reading documents. InProceedings of the 2016 conference on empirical methods in natural language processing. Association for Computational Linguistics, Austin, Texas, 1400–1409

    2016

  34. [34]

    OpenAI. 2022. Introducing ChatGPT. https://openai.com/index/chatgpt/

    2022

  35. [35]

    OpenAI. 2024. Hello gpt-4o. https://openai.com/index/hello-gpt-4o/

    2024

  36. [36]

    Palantir. 2024. Connecting AI to Decisions with the Palantir Ontol- ogy. https://blog.palantir.com/connecting-ai-to-decisions-with-the-palantir- ontology-c73f7b0a1a72. Accessed: 2026-04-29

    2024

  37. [37]

    Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu

  38. [38]

    IEEE Transactions on Knowledge and Data Engineering36(7), 3580–3599 (2024)

    Unifying Large Language Models and Knowledge Graphs: A Roadmap. IEEE Transactions on Knowledge and Data Engineering36, 7 (2024), 3580–3599. https://doi.org/10.1109/TKDE.2024.3352100

    work page doi:10.1109/tkde.2024.3352100 2024

  39. [39]

    Kashif Rabbani, Matteo Lissandrini, and Katja Hose. 2023. Extraction of Validating Shapes from Very Large Knowledge Graphs.Proceedings of the VLDB Endowment 16, 5 (Jan. 2023), 1023–1032. https://doi.org/10.14778/3579075.3579078

    work page doi:10.14778/3579075.3579078 2023

  40. [40]

    Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. InProceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). 3982–3992

    2019

  41. [41]

    Apoorv Saxena, Adrian Kochsiek, and Rainer Gemulla. 2022. Sequence-to- sequence knowledge graph completion and question answering. InProceedings of the 60th annual meeting of the association for computational linguistics (vol- ume 1: long papers). Association for Computational Linguistics, Dublin, Ireland, 2814–2828

    2022

  42. [42]

    Jiaxin Shi, Shulin Cao, Lei Hou, Juanzi Li, and Hanwang Zhang. 2021. Transfernet: An effective and transparent framework for multi-hop question answering over relation graph. InProceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, 4149–4158. 13

    2021

  43. [43]

    Haitian Sun, Tania Bedrax-Weiss, and William Cohen. 2019. Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text. InProceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computatio...

    2019

  44. [44]

    Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhut- dinov, and William Cohen. 2018. Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text. InProceedings of the 2018 Conference on Em- pirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 4231–4242

    2018

  45. [45]

    Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel Ni, Heung-Yeung Shum, and Jian Guo. 2024. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. InThe Twelfth International Conference on Learning Representations. OpenRe- view.net, Vienna, Austria, 31. https://openreview.net/forum?id...

    2024

  46. [46]

    Alon Talmor and Jonathan Berant. 2018. The Web as a Knowledge-Base for Answering Complex Questions. InProceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Association for Computational Linguistics, New Orleans, Louisiana, 641–651

    2018

  47. [47]

    Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, and Wenjie Zhang

  48. [48]

    InProceedings of the ACM on Web Conference 2025(Sydney NSW, Australia)(WWW ’25)

    Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning. InProceedings of the ACM on Web Conference 2025(Sydney NSW, Australia)(WWW ’25). Association for Computing Machinery, New York, NY, USA, 3505–3522. https://doi.org/10.1145/3696410.3714892

    work page doi:10.1145/3696410.3714892 2025

  49. [49]

    Anagnostopoulos, Sue Bello, Kai Blumberg, Rhiannon Cameron, Leigh Carmody, Alexander D

    Sabrina Toro, Anna V. Anagnostopoulos, Sue Bello, Kai Blumberg, Rhiannon Cameron, Leigh Carmody, Alexander D. Diehl, Damion M. Dooley, William Duncan, Petra Fey, Pascale Gaudet, Nomi L. Harris, marcin p. joachimiak, Leila Kiani, Tiago Lubiana, Monica C. Munoz-Torres, Shawn T. O’Neil, David Osumi- Sutherland, Aleix Puig, Justin Reese, Leonore Reiser, Sofia...

    2024

  50. [50]

    Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. https://doi.org/10.48550/arXiv.2307.09288 arXiv:2307.09288 [cs.CL]

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2307.09288 2023

  51. [51]

    Yilin Wen, Zifeng Wang, and Jimeng Sun. 2024. MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). Association for Computational Linguistics, Bangkok, Thai...

    work page doi:10.18653/v1/2024.acl-long.558 2024

  52. [52]

    Tian Yang, Yupeng Mei, Ling Xu, Huihui Yu, and Yingyi Chen. 2024. Applica- tion of question answering systems for intelligent agriculture production and sustainable management: A review.Resources, Conservation and Recycling204 (2024), 107497. https://doi.org/10.1016/j.resconrec.2024.107497

    work page doi:10.1016/j.resconrec.2024.107497 2024

  53. [53]

    Wen-tau Yih, Matthew Richardson, Christopher Meek, Ming-Wei Chang, and Jina Suh. 2016. The value of semantic parse labeling for knowledge base question answering. InProceedings of the 54th Annual Meeting of the Association for Com- putational Linguistics (Volume 2: Short Papers). Association for Computational Linguistics, Berlin, Germany, 201–206

    2016

  54. [54]

    Changsen Yuan, Rui Lin, and Cunhan Guo. 2026. Reliable reasoning: Learning and inference based on the ability of large language models.Applied Soft Computing 190 (2026), 114618

    2026

  55. [55]

    Han Zhang, Langshi Zhou, and Hanfang Yang. 2025. Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection. https://doi.org/10. 48550/arXiv.2502.14932 arXiv:2502.14932 [cs.CL]

    arXiv 2025

  56. [56]

    Jing Zhang, Xiaokang Zhang, Jifan Yu, Jian Tang, Jie Tang, Cuiping Li, and Hong Chen. 2022. Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering. InProceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Dublin, Ireland, 5773–5784

    2022

  57. [57]

    Yuyu Zhang, Hanjun Dai, Zornitsa Kozareva, Alexander Smola, and Le Song

  58. [58]

    In Proceedings of the AAAI conference on artificial intelligence, Vol

    Variational reasoning for question answering with knowledge graph. In Proceedings of the AAAI conference on artificial intelligence, Vol. 32. AAAI Press, New Orleans, Lousiana, USA, 6069–6076. 14