---
title: "TRACE — paper by Wang et al. (2026) — summary and ideas"
description: "An LLM retriever proposes the top-k relations, and a re-ranker reorders them using the current path and the accumulated… 53 references."
authors: ["Yingxu Wang", "Jiaxin Huang", "Mengzhu Wang", "Nan Yin"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.89/"
doi: "10.18653/v1/2026.findings-acl.89"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2026-trace-experiential-framework-coherent-multi/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-trace-experiential-framework-coherent-multi/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/46/) / TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering

# TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering

**Authors:** Yingxu Wang, [Jiaxin Huang](https://md.research.elamur.ai/free/en/authors/jiaxin-huang/), Mengzhu Wang and [Nan Yin](https://md.research.elamur.ai/free/en/authors/nan-yin/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.89/) · [PDF](https://aclanthology.org/2026.findings-acl.89.pdf) · [DOI 10.18653/v1/2026.findings-acl.89](https://doi.org/10.18653/v1/2026.findings-acl.89) · [OpenAlex](https://openalex.org/W7166810477)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Answering complex questions over a knowledge graph often requires several hops along relations. LLM-based systems that choose one relation at a time tend to lose track of what earlier hops meant, and they repeat unproductive searches. TRACE, an acronym describing reasoning that keeps track of its trajectory while drawing on adaptive context and priors for exploration, tackles both problems through three modules driven by LLMs:

- **Running context.** After each step, the relations traversed so far are rewritten as a short plain-language statement of the intended reasoning. The next choice is then conditioned on the question plus this running description.
- **Learned lessons.** Finished trajectories are summarized and periodically condensed into general lessons about which exploration habits succeed and which hit dead ends. A trajectory counts as finished when it reaches the hop limit L or cannot be extended.
- **Re-ranking.** An LLM retriever proposes the top-k relations, and a re-ranker reorders them using the current path and the accumulated lessons.

On WebQSP and CWQ, TRACE outperforms state-of-the-art baselines. This suggests that reusing past search experience makes multi-hop KGQA more coherent and less wasteful.

## Key points
- The three components are Dynamic Context Generation, Exploration Generalization and Dual-Feedback Re-ranking. The task is framed as sequential relation selection from topic entities toward answer entities.
- Benchmarks are WebQSP and CWQ, reported with Hits and F1. Sensitivity analysis covers the number of candidate relations k, the path length L and a threshold ζ. Exact scores fall in the part of the provided text that was cut out.
- In a case study about a film with Kim Richards produced by Ann Marie Sanerlin, Llama-2-13B, Qwen-3-14B, GPT 4.1 and GPT 4.1-mini all gave hallucinated answers. TRACE found "Race to Witch Mountain" and learned to favour production links over cast-related loops.
- Stated limitations are reliance on hand-crafted prompts and priors, and notable inference cost from combining several reasoning components.
- Authors are affiliated with MBZUAI, Hebei University of Technology and City University of Hong Kong. The paper appears in Findings of ACL 2026, pp. 1830–1851.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [City University of Hong Kong](https://md.research.elamur.ai/free/en/universities/city-university-of-hong-kong/) — University, Hong Kong, China · 45 works · 3,014 citations
- [Hebei University of Technology](https://md.research.elamur.ai/free/en/universities/hebei-university-of-technology/) — University, Tianjin, China · 2 works · 8 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 441 works · [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) · 192 works

## Cite

Cite as: Yingxu Wang, Jiaxin Huang, Mengzhu Wang and Nan Yin. 2026. TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wang2026trace,
  title = {{TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering}},
  author = {Yingxu Wang, Jiaxin Huang, Mengzhu Wang and Nan Yin},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.89},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.89}
}
```

- [← previous TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG](https://md.research.elamur.ai/free/en/papers/lu-2026-tpa-next-token-probability-attribution/)
- [next → TRACE: Two-Phase RL for Causal Graph Exploration and Deeper Psychological Intervention in Dynamic Counseling Scenarios](https://md.research.elamur.ai/free/en/papers/tang-2026-trace-two-phase-rl-causal/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/46/)

## References

53 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jinheon Baek, Alham Fikri Aji, and Amir Saffari. 2023. [Knowledge-augmented language model prompting for zero-shot knowledge graph question answering](https://md.research.elamur.ai/free/en/papers/baek-2023-knowledge-augmented-language-model-prompting/). arXiv preprint arXiv:2306.04136.
2. Krisztian Balog and Tom Kenter. 2019. Personal knowledge graphs: A research agenda. In Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval, pages 217–220. [find](https://scholar.google.com/scholar?q=Krisztian+Balog+and+Tom+Kenter%2E+2019%2E+Personal+knowledge+graphs%3A+A+research+agenda%2E+In+Proceedings+of+the+2019+ACM+SIGIR+International+Conference+on+Theory+of+Information+Retrieval%2C+pages+217%E2%80%93220%2E)
3. Zhenni Bi, Kai Han, Chuanjian Liu, Yehui Tang, and Yunhe Wang. 2024. [Forest-of-thought: Scaling test-time compute for enhancing llm reasoning](https://md.research.elamur.ai/free/en/papers/bi-2024-forest-thought-scaling-test-time/). arXiv preprint arXiv:2412.09078.
4. Hyeong Kyu Choi, Seunghun Lee, Jaewon Chu, and Hyunwoo J Kim. 2023. Nutrea: Neural tree search for context-guided multi-hop kgqa. Proceedings of the Conference on Neural Information Processing Systems, 36:35954–35965. [find](https://scholar.google.com/scholar?q=Hyeong+Kyu+Choi%2C+Seunghun+Lee%2C+Jaewon+Chu%2C+and+Hyunwoo+J+Kim%2E+2023%2E+Nutrea%3A+Neural+tree+search+for+context%2Dguided+multi%2Dhop+kgqa%2E+Proceedings+of+the+Conference+on+Neural+Information+Processing+Systems)
5. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, and 1 others. 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research, 25(70):1–53. [find](https://scholar.google.com/scholar?q=Hyung+Won+Chung%2C+Le+Hou%2C+Shayne+Longpre%2C+Barret+Zoph%2C+Yi+Tay%2C+William+Fedus%2C+Yunxuan+Li%2C+Xuezhi+Wang%2C+Mostafa+Dehghani%2C+Siddhartha+Brahma%2C+and+1+others%2E+2024%2E+Scaling+instruction%2Dfinetuned+language+mo)
6. Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, and Andrew McCallum. 2018. Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning. In Proceedings of the International Conference on… [find](https://scholar.google.com/scholar?q=Rajarshi+Das%2C+Shehzaad+Dhuliawala%2C+Manzil+Zaheer%2C+Luke+Vilnis%2C+Ishan+Durugkar%2C+Akshay+Krishnamurthy%2C+Alex+Smola%2C+and+Andrew+McCallum%2E+2018%2E+Go+for+a+walk+and+arrive+at+the+answer%3A+Reasoning+over+paths)
7. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv e-prints, pages arXiv–2407.
8. Siyuan Fang, Kaijing Ma, Tianyu Zheng, Xinrun Du, Ningxuan Lu, Ge Zhang, and Qingkun Tang. 2024. Karpa: A training-free method of adapting knowledge graph as references for large language model’s reasoning path aggregation. arXiv preprint arXiv:2412.20995. [find](https://scholar.google.com/scholar?q=Siyuan+Fang%2C+Kaijing+Ma%2C+Tianyu+Zheng%2C+Xinrun+Du%2C+Ningxuan+Lu%2C+Ge+Zhang%2C+and+Qingkun+Tang%2E+2024%2E+Karpa%3A+A+training%2Dfree+method+of+adapting+knowledge+graph+as+references+for+large+language+model%E2%80%99s+reas)
9. Qingyu Guo, Fuzhen Zhuang, Chuan Qin, Hengshu Zhu, Xing Xie, Hui Xiong, and Qing He. 2020. A survey on knowledge graph-based recommender systems. IEEE Transactions on Knowledge and Data Engineering, 34:3549–3568. [find](https://scholar.google.com/scholar?q=Qingyu+Guo%2C+Fuzhen+Zhuang%2C+Chuan+Qin%2C+Hengshu+Zhu%2C+Xing+Xie%2C+Hui+Xiong%2C+and+Qing+He%2E+2020%2E+A+survey+on+knowledge+graph%2Dbased+recommender+systems%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering%2C+3)
10. Gaole He, Yunshi Lan, Jing Jiang, Wayne Xin Zhao, and Ji-Rong Wen. 2021. Improving multi-hop knowledge base question answering by learning intermediate supervision signals. In Proceedings of the International ACM Conference on Web Search & Data Mining, pages 553–561. [find](https://scholar.google.com/scholar?q=Gaole+He%2C+Yunshi+Lan%2C+Jing+Jiang%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2021%2E+Improving+multi%2Dhop+knowledge+base+question+answering+by+learning+intermediate+supervision+signals%2E+In+Proceedings+of+the+Inter)
11. Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. 2023. [Large language models cannot self-correct reasoning yet](https://md.research.elamur.ai/free/en/papers/huang-2023-large-language-models-cannot-self/). arXiv preprint arXiv:2310.01798.
12. 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. arXiv preprint arXiv:2401.00158. [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Wayne+Xin+Zhao%2C+Yaliang+Li%2C+and+Ji%2DRong+Wen%2E+2023%2E+Reasoninglm%3A+Enabling+structural+subgraph+reasoning+in+pre%2Dtrained+language+models+for+question+answering+over+knowledge+grap)
13. Jinhao Jiang, Kun Zhou, Wayne Xin Zhao, and Ji-Rong Wen. 2022. Unikgqa: Unified retrieval and reasoning for solving multi-hop question answering over knowledge graph. arXiv preprint arXiv:2212.00959. [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2022%2E+Unikgqa%3A+Unified+retrieval+and+reasoning+for+solving+multi%2Dhop+question+answering+over+knowledge+graph%2E+arXiv+preprint+arXiv%3A2212%2E00959%2E)
14. Mayank Kejriwal and Pedro A. Szekely. 2017. Knowledge graphs for social good: An entity-centric search engine for the human trafficking domain. IEEE Transactions on Big Data, 8:592–606. [find](https://scholar.google.com/scholar?q=Mayank+Kejriwal+and+Pedro+A%2E+Szekely%2E+2017%2E+Knowledge+graphs+for+social+good%3A+An+entity%2Dcentric+search+engine+for+the+human+trafficking+domain%2E+IEEE+Transactions+on+Big+Data%2C+8%3A592%E2%80%93606%2E)
15. Yunshi Lan and Jing Jiang. 2020. Query graph generation for answering multi-hop complex questions from knowledge bases. Proceedings of the Annual Meeting of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yunshi+Lan+and+Jing+Jiang%2E+2020%2E+Query+graph+generation+for+answering+multi%2Dhop+complex+questions+from+knowledge+bases%2E+Proceedings+of+the+Annual+Meeting+of+the+Association+for+Computational+Linguisti)
16. Seongmin Lee, Jaewook Shin, Youngjin Ahn, Seokin Seo, Ohjoon Kwon, and Kee-Eung Kim. 2024. Zero-shot multi-hop question answering via monte-carlo tree search with large language models. arXiv preprint arXiv:2409.19382. — [arXiv:2409.19382](https://arxiv.org/abs/2409.19382) [find](https://scholar.google.com/scholar?q=Seongmin+Lee%2C+Jaewook+Shin%2C+Youngjin+Ahn%2C+Seokin+Seo%2C+Ohjoon+Kwon%2C+and+Kee%2DEung+Kim%2E+2024%2E+Zero%2Dshot+multi%2Dhop+question+answering+via+monte%2Dcarlo+tree+search+with+large+language+models%2E+arXiv+preprint)
17. Guangyi Liu, Yongqi Zhang, Yong Li, and Quanming Yao. 2025. Dual reasoning: A gnn-llm collaborative framework for knowledge graph question answering. In The Second Conference on Parsimony and Learning (Proceedings Track). [find](https://scholar.google.com/scholar?q=Guangyi+Liu%2C+Yongqi+Zhang%2C+Yong+Li%2C+and+Quanming+Yao%2E+2025%2E+Dual+reasoning%3A+A+gnn%2Dllm+collaborative+framework+for+knowledge+graph+question+answering%2E+In+The+Second+Conference+on+Parsimony+and+Learning)
18. Hanmeng Liu, Ruoxi Ning, Zhiyang Teng, Jian Liu, Qiji Zhou, and Yue Zhang. 2023. [Evaluating the logical reasoning ability of chatgpt and gpt-4](https://md.research.elamur.ai/free/en/papers/liu-2023-evaluating-logical-reasoning-ability-chatgpt/). arXiv preprint arXiv:2304.03439.
19. Lingyuan Liu, Huifang Du, Xiaolian Zhang, Mengying Guo, Haofen Wang, and Meng Wang. 2024. A question-answering assistant over personal knowledge graph. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2708–2712. [find](https://scholar.google.com/scholar?q=Lingyuan+Liu%2C+Huifang+Du%2C+Xiaolian+Zhang%2C+Mengying+Guo%2C+Haofen+Wang%2C+and+Meng+Wang%2E+2024%2E+A+question%2Danswering+assistant+over+personal+knowledge+graph%2E+In+Proceedings+of+the+47th+International+ACM+SIG)
20. Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2023. Reasoning on graphs: Faithful and interpretable large language model reasoning. arXiv preprint arXiv:2310.01061. [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Yuan%2DFang+Li%2C+Gholamreza+Haffari%2C+and+Shirui+Pan%2E+2023%2E+Reasoning+on+graphs%3A+Faithful+and+interpretable+large+language+model+reasoning%2E+arXiv+preprint+arXiv%3A2310%2E01061%2E)
21. Chuangtao Ma, Yongrui Chen, Tianxing Wu, Arijit Khan, and Haofen Wang. 2025a. Large language models meet knowledge graphs for question answering: Synthesis and opportunities. arXiv preprint arXiv:2505.20099. [find](https://scholar.google.com/scholar?q=Chuangtao+Ma%2C+Yongrui+Chen%2C+Tianxing+Wu%2C+Arijit+Khan%2C+and+Haofen+Wang%2E+2025a%2E+Large+language+models+meet+knowledge+graphs+for+question+answering%3A+Synthesis+and+opportunities%2E+arXiv+preprint+arXiv%3A2505)
22. Jie Ma, Zhitao Gao, Qi Chai, Wangchun Sun, Pinghui Wang, Hongbin Pei, Jing Tao, Lingyun Song, Jun Liu, Chen Zhang, and 1 others. 2025b. Debate on graph: a flexible and reliable reasoning framework for large language models. In Proceedings of the AAAI Conference on Artificial Intelligence, 23, pages… [find](https://scholar.google.com/scholar?q=Jie+Ma%2C+Zhitao+Gao%2C+Qi+Chai%2C+Wangchun+Sun%2C+Pinghui+Wang%2C+Hongbin+Pei%2C+Jing+Tao%2C+Lingyun+Song%2C+Jun+Liu%2C+Chen+Zhang%2C+and+1+others%2E+2025b%2E+Debate+on+graph%3A+a+flexible+and+reliable+reasoning+framework+for)
23. Jie Ma, Ning Qu, Zhitao Gao, Rui Xing, Jun Liu, Hongbin Pei, Jiang Xie, Linyun Song, Pinghui Wang, Jing Tao, and 1 others. 2025c. Deliberation on priors: Trustworthy reasoning of large language models on knowledge graphs. arXiv preprint arXiv:2505.15210. — [arXiv:2505.15210](https://arxiv.org/abs/2505.15210) [find](https://scholar.google.com/scholar?q=Jie+Ma%2C+Ning+Qu%2C+Zhitao+Gao%2C+Rui+Xing%2C+Jun+Liu%2C+Hongbin+Pei%2C+Jiang+Xie%2C+Linyun+Song%2C+Pinghui+Wang%2C+Jing+Tao%2C+and+1+others%2E+2025c%2E+Deliberation+on+priors%3A+Trustworthy+reasoning+of+large+language+models)
24. Shengjie Ma, Chengjin Xu, Xuhui Jiang, Muzhi Li, Huaren Qu, Cehao Yang, Jiaxin Mao, and Jian Guo. 2024. Think-on-graph 2.0: Deep and faithful large language model reasoning with knowledge-guided retrieval augmented generation. arXiv preprint arXiv:2407.10805. — [arXiv:2407.10805](https://arxiv.org/abs/2407.10805) [find](https://scholar.google.com/scholar?q=Shengjie+Ma%2C+Chengjin+Xu%2C+Xuhui+Jiang%2C+Muzhi+Li%2C+Huaren+Qu%2C+Cehao+Yang%2C+Jiaxin+Mao%2C+and+Jian+Guo%2E+2024%2E+Think%2Don%2Dgraph+2%2E0%3A+Deep+and+faithful+large+language+model+reasoning+with+knowledge%2Dguided+retri)
25. Costas Mavromatis and George Karypis. 2024. Gnn-rag: Graph neural retrieval for large language model reasoning. arXiv preprint arXiv:2405.20139. [find](https://scholar.google.com/scholar?q=Costas+Mavromatis+and+George+Karypis%2E+2024%2E+Gnn%2Drag%3A+Graph+neural+retrieval+for+large+language+model+reasoning%2E+arXiv+preprint+arXiv%3A2405%2E20139%2E)
26. Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. 2016. Key-value memory networks for directly reading documents. arXiv preprint arXiv:1606.03126. [find](https://scholar.google.com/scholar?q=Alexander+Miller%2C+Adam+Fisch%2C+Jesse+Dodge%2C+Amir%2DHossein+Karimi%2C+Antoine+Bordes%2C+and+Jason+Weston%2E+2016%2E+Key%2Dvalue+memory+networks+for+directly+reading+documents%2E+arXiv+preprint+arXiv%3A1606%2E03126%2E)
27. Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. 2023. Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies. arXiv preprint arXiv:2308.03188. [find](https://scholar.google.com/scholar?q=Liangming+Pan%2C+Michael+Saxon%2C+Wenda+Xu%2C+Deepak+Nathani%2C+Xinyi+Wang%2C+and+William+Yang+Wang%2E+2023%2E+Automatically+correcting+large+language+models%3A+Surveying+the+landscape+of+diverse+self%2Dcorrection+stra)
28. Luís Roque. 2025. The evolution of llama: From llama 1 to llama 3.1. [find](https://scholar.google.com/scholar?q=Lu%C3%ADs+Roque%2E+2025%2E+The+evolution+of+llama%3A+From+llama+1+to+llama+3%2E1%2E)
29. Apoorv Saxena, Adrian Kochsiek, and Rainer Gemulla. 2022. Sequence-to-sequence knowledge graph completion and question answering. arXiv preprint arXiv:2203.10321. [find](https://scholar.google.com/scholar?q=Apoorv+Saxena%2C+Adrian+Kochsiek%2C+and+Rainer+Gemulla%2E+2022%2E+Sequence%2Dto%2Dsequence+knowledge+graph+completion+and+question+answering%2E+arXiv+preprint+arXiv%3A2203%2E10321%2E)
30. Apoorv Saxena, Aditay Tripathi, and Partha Talukdar. 2020. [Improving multi-hop question answering over knowledge graphs using knowledge base embeddings](https://md.research.elamur.ai/free/en/papers/saxena-2020-improving-multi-hop-question-answering/). In Proceedings of the 58th annual meeting of the association for computational linguistics, pages 4498– 4507.
31. John Schulman, Barret Zoph, Christina Kim, Jacob Hilton, Jacob Menick, Jiayi Weng, Juan Felipe Ceron Uribe, Liam Fedus, Luke Metz, Michael Pokorny, and 1 others. 2022. Chatgpt: Optimizing language models for dialogue. OpenAI blog, 2(4). [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Barret+Zoph%2C+Christina+Kim%2C+Jacob+Hilton%2C+Jacob+Menick%2C+Jiayi+Weng%2C+Juan+Felipe+Ceron+Uribe%2C+Liam+Fedus%2C+Luke+Metz%2C+Michael+Pokorny%2C+and+1+others%2E+2022%2E+Chatgpt%3A+Optimizing+language+mod)
32. Tiesunlong Shen, Jin Wang, Xuejie Zhang, and Erik Cambria. 2025. Reasoning with trees: Faithful question answering over knowledge graph. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 3138–3157. [find](https://scholar.google.com/scholar?q=Tiesunlong+Shen%2C+Jin+Wang%2C+Xuejie+Zhang%2C+and+Erik+Cambria%2E+2025%2E+Reasoning+with+trees%3A+Faithful+question+answering+over+knowledge+graph%2E+In+Proceedings+of+the+Annual+Meeting+of+the+Association+for+Com)
33. 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. arXiv preprint arXiv:2104.07302. [find](https://scholar.google.com/scholar?q=Jiaxin+Shi%2C+Shulin+Cao%2C+Lei+Hou%2C+Juanzi+Li%2C+and+Hanwang+Zhang%2E+2021%2E+Transfernet%3A+An+effective+and+transparent+framework+for+multi%2Dhop+question+answering+over+relation+graph%2E+arXiv+preprint+arXiv%3A2104)
34. Yuan Sui, Yufei He, Nian Liu, Xiaoxin He, Kun Wang, and Bryan Hooi. 2024. Fidelis: Faithful reasoning in large language model for knowledge graph question answering. arXiv preprint arXiv:2405.13873. — [arXiv:2405.13873](https://arxiv.org/abs/2405.13873) [find](https://scholar.google.com/scholar?q=Yuan+Sui%2C+Yufei+He%2C+Nian+Liu%2C+Xiaoxin+He%2C+Kun+Wang%2C+and+Bryan+Hooi%2E+2024%2E+Fidelis%3A+Faithful+reasoning+in+large+language+model+for+knowledge+graph+question+answering%2E+arXiv+preprint+arXiv%3A2405%2E13873%2E+%E2%80%94)
35. Haitian Sun, Tania Bedrax-Weiss, and William W Cohen. 2019. Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text. arXiv preprint arXiv:1904.09537. [find](https://scholar.google.com/scholar?q=Haitian+Sun%2C+Tania+Bedrax%2DWeiss%2C+and+William+W+Cohen%2E+2019%2E+Pullnet%3A+Open+domain+question+answering+with+iterative+retrieval+on+knowledge+bases+and+text%2E+arXiv+preprint+arXiv%3A1904%2E09537%2E)
36. Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, and William W Cohen. 2018. Open domain question answering using early fusion of knowledge bases and text. arXiv preprint arXiv:1809.00782. [find](https://scholar.google.com/scholar?q=Haitian+Sun%2C+Bhuwan+Dhingra%2C+Manzil+Zaheer%2C+Kathryn+Mazaitis%2C+Ruslan+Salakhutdinov%2C+and+William+W+Cohen%2E+2018%2E+Open+domain+question+answering+using+early+fusion+of+knowledge+bases+and+text%2E+arXiv+prep)
37. Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel M Ni, Heung-Yeung Shum, and Jian Guo. 2023. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. arXiv preprint arXiv:2307.07697. [find](https://scholar.google.com/scholar?q=Jiashuo+Sun%2C+Chengjin+Xu%2C+Lumingyuan+Tang%2C+Saizhuo+Wang%2C+Chen+Lin%2C+Yeyun+Gong%2C+Lionel+M+Ni%2C+Heung%2DYeung+Shum%2C+and+Jian+Guo%2E+2023%2E+Think%2Don%2Dgraph%3A+Deep+and+responsible+reasoning+of+large+language+model)
38. Alon Talmor and Jonathan Berant. 2018. [The web as a knowledge-base for answering complex questions](https://md.research.elamur.ai/free/en/papers/talmor-2018-web-as-knowledge-base-answering/). arXiv preprint arXiv:1803.06643.
39. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B Hashimoto. 2023. Stanford alpaca: An instruction-following llama model. [find](https://scholar.google.com/scholar?q=Rohan+Taori%2C+Ishaan+Gulrajani%2C+Tianyi+Zhang%2C+Yann+Dubois%2C+Xuechen+Li%2C+Carlos+Guestrin%2C+Percy+Liang%2C+and+Tatsunori+B+Hashimoto%2E+2023%2E+Stanford+alpaca%3A+An+instruction%2Dfollowing+llama+model%2E)
40. Qwen Team. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwen2+technical+report%2E+arXiv+preprint+arXiv%3A2407%2E10671%2E)
41. Hongwei Wang, Miao Zhao, Xing Xie, Wenjie Li, and Minyi Guo. 2019. Knowledge graph convolutional networks for recommender systems. In The world wide web conference, pages 3307–3313. [find](https://scholar.google.com/scholar?q=Hongwei+Wang%2C+Miao+Zhao%2C+Xing+Xie%2C+Wenjie+Li%2C+and+Minyi+Guo%2E+2019%2E+Knowledge+graph+convolutional+networks+for+recommender+systems%2E+In+The+world+wide+web+conference%2C+pages+3307%E2%80%933313%2E)
42. Keheng Wang, Feiyu Duan, Sirui Wang, Peiguang Li, Yunsen Xian, Chuantao Yin, Wenge Rong, and Zhang Xiong. 2023. Knowledge-driven cot: Exploring faithful reasoning in llms for knowledge-intensive question answering. arXiv preprint arXiv:2308.13259. — [arXiv:2308.13259](https://arxiv.org/abs/2308.13259) [find](https://scholar.google.com/scholar?q=Keheng+Wang%2C+Feiyu+Duan%2C+Sirui+Wang%2C+Peiguang+Li%2C+Yunsen+Xian%2C+Chuantao+Yin%2C+Wenge+Rong%2C+and+Zhang+Xiong%2E+2023%2E+Knowledge%2Ddriven+cot%3A+Exploring+faithful+reasoning+in+llms+for+knowledge%2Dintensive+quest)
43. Yingxu Wang, Shiqi Fan, Mengzhu Wang, Siyang Gao, Chao Wang, and Nan Yin. 2026. DAMR: Efficient and adaptive context-aware knowledge graph question answering with LLM-guided MCTS. In Proceedings of the International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yingxu+Wang%2C+Shiqi+Fan%2C+Mengzhu+Wang%2C+Siyang+Gao%2C+Chao+Wang%2C+and+Nan+Yin%2E+2026%2E+DAMR%3A+Efficient+and+adaptive+context%2Daware+knowledge+graph+question+answering+with+LLM%2Dguided+MCTS%2E+In+Proceedings+of+th)
44. 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. arXiv preprint arXiv:2202.13296. [find](https://scholar.google.com/scholar?q=Jing+Zhang%2C+Xiaokang+Zhang%2C+Jifan+Yu%2C+Jian+Tang%2C+Jie+Tang%2C+Cuiping+Li%2C+and+Hong+Chen%2E+2022%2E+Subgraph+retrieval+enhanced+model+for+multi%2Dhop+knowledge+base+question+answering%2E+arXiv+preprint+arXiv%3A2202)
45. Zhiqiang Zhang and Wen Zhao. 2025. A collaborative reasoning framework powered by reinforcement learning and large language models for complex questions answering over knowledge graph. In Proceedings of the 31st International Conference on Computational Linguistics, pages 10672–10684. [find](https://scholar.google.com/scholar?q=Zhiqiang+Zhang+and+Wen+Zhao%2E+2025%2E+A+collaborative+reasoning+framework+powered+by+reinforcement+learning+and+large+language+models+for+complex+questions+answering+over+knowledge+graph%2E+In+Proceedings+)
46. Xuejiao Zhao, Huanhuan Chen, Zhenchang Xing, and Chunyan Miao. 2020. Brain-inspired search engine assistant based on knowledge graph. IEEE Transactions on Neural Networks and Learning Systems, 34:4386–4400. [find](https://scholar.google.com/scholar?q=Xuejiao+Zhao%2C+Huanhuan+Chen%2C+Zhenchang+Xing%2C+and+Chunyan+Miao%2E+2020%2E+Brain%2Dinspired+search+engine+assistant+based+on+knowledge+graph%2E+IEEE+Transactions+on+Neural+Networks+and+Learning+Systems%2C+34%3A4386)
47. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Proceedings of the Conference on Neural Information Processing Systems, 35:24824–24837.
48. Tsung-Han Wu, Long Lian, Joseph E Gonzalez, Boyi Li, and Trevor Darrell. 2024. Self-correcting llm-controlled diffusion models. In The IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6327–6336. [find](https://scholar.google.com/scholar?q=Tsung%2DHan+Wu%2C+Long+Lian%2C+Joseph+E+Gonzalez%2C+Boyi+Li%2C+and+Trevor+Darrell%2E+2024%2E+Self%2Dcorrecting+llm%2Dcontrolled+diffusion+models%2E+In+The+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition%2C+p)
49. Wenhan Xiong, Thien Hoang, and William Yang Wang. 2017. Deeppath: A reinforcement learning method for knowledge graph reasoning. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 564–573. [find](https://scholar.google.com/scholar?q=Wenhan+Xiong%2C+Thien+Hoang%2C+and+William+Yang+Wang%2E+2017%2E+Deeppath%3A+A+reinforcement+learning+method+for+knowledge+graph+reasoning%2E+In+Proceedings+of+the+Conference+on+Empirical+Methods+in+Natural+Langua)
50. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In International Conference on Learning Representations (ICLR).
51. Tianjun Yao, Haoxuan Li, Zhiqiang Shen, Pan Li, Tongliang Liu, and Kun Zhang. 2025. Learning efficient and generalizable graph retriever for knowledge-graph question answering. arXiv preprint arXiv:2506.09645. — [arXiv:2506.09645](https://arxiv.org/abs/2506.09645) [find](https://scholar.google.com/scholar?q=Tianjun+Yao%2C+Haoxuan+Li%2C+Zhiqiang+Shen%2C+Pan+Li%2C+Tongliang+Liu%2C+and+Kun+Zhang%2E+2025%2E+Learning+efficient+and+generalizable+graph+retriever+for+knowledge%2Dgraph+question+answering%2E+arXiv+preprint+arXiv%3A25)
52. 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](https://md.research.elamur.ai/free/en/papers/yih-2016-value-semantic-parse-labeling-knowledge/). In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 201–206.
53. Donghan Yu, Sheng Zhang, Patrick Ng, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Yiqun Hu, William Wang, Zhiguo Wang, and Bing Xiang. 2022. Decaf: Joint decoding of answers and logical forms for question answering over knowledge bases. arXiv preprint arXiv:2210.00063. [find](https://scholar.google.com/scholar?q=Donghan+Yu%2C+Sheng+Zhang%2C+Patrick+Ng%2C+Henghui+Zhu%2C+Alexander+Hanbo+Li%2C+Jun+Wang%2C+Yiqun+Hu%2C+William+Wang%2C+Zhiguo+Wang%2C+and+Bing+Xiang%2E+2022%2E+Decaf%3A+Joint+decoding+of+answers+and+logical+forms+for+questi)

*Updated 1 November 2026*