---
title: "Which bird does not have wings — paper by Shim et al. (2026)"
description: "The authors define a new task, NEST (NEgative-conSTrained) KGQA, in which every question has at least one negative… 51 references."
authors: ["Midan Shim", "Seokju Hwang", "KaeHyun Um", "Kyong-Ho Lee"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1132/"
doi: "10.18653/v1/2026.findings-acl.1132"
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/shim-2026-which-bird-does-not-have/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shim-2026-which-bird-does-not-have/)

[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/56/) / Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement

# Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement

**Authors:** [Midan Shim](https://md.research.elamur.ai/free/en/authors/midan-shim/), [Seokju Hwang](https://md.research.elamur.ai/free/en/authors/seokju-hwang/), [KaeHyun Um](https://md.research.elamur.ai/free/en/authors/kaehyun-um/) and [Kyong-Ho Lee](https://md.research.elamur.ai/free/en/authors/kyong-ho-lee/) · **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.1132/) · [PDF](https://aclanthology.org/2026.findings-acl.1132.pdf) · [DOI 10.18653/v1/2026.findings-acl.1132](https://doi.org/10.18653/v1/2026.findings-acl.1132) · [OpenAlex](https://openalex.org/W7166865582)

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

## Summary
Most KGQA benchmarks and methods focus on positive constraints and calculations such as counting or comparison. Questions with true negation, like asking for a rocket *not* made by a given manufacturer, are largely ignored. Some existing datasets contain "not", but those cases usually turn out to be comparisons. The authors define a new task, NEST (NEgative-conSTrained) KGQA, in which every question has at least one negative constraint and more than one constraint overall.

They make three contributions:
- **NestKGQA**, a dataset built by extending earlier benchmarks. An LLM drafted it, and graduate annotators then verified and corrected it.
- **PyLF**, a Python-style logical form that adds an explicit negation flag to symbolic operators, keeping queries both expressive and readable.
- **CUCKOO**, a few-shot, in-context semantic-parsing framework. It drafts a constraint-aware logical form and grounds it in the KG schema so the resulting queries are semantically executable. It revises the draft only if the query returns nothing.

CUCKOO achieves the best or second-best results on both standard and NEST benchmarks. This matters because LLMs are known to handle negation poorly.

## Key points
- **Constraint types:** constraints are positive, negative or calculation-based. A negative constraint holds when a schema-valid triple is absent from the KG, under a closed-world assumption.
- **CUCKOO pipeline:** the framework has three stages.
  - Constraint-aware draft generation.
  - Schema-guided semantic matching, which replaces brute-force matching. Brute force gave lower scores because it produced more wrong but executable queries.
  - Self-directed refinement, triggered only on empty results.
- **Superlatives on GrailQA:** CUCKOO raised the score from 3.1 (KB-Coder) to 53.1. It also kept its lead over KB-Coder as the number of constraints increased.
- **Efficiency versus KB-Coder:**
  - About 12.3% more input tokens.
  - Roughly 1.6× the inference time (38.45s vs 23.76s per question).
  - Slightly lower CPU memory (4.4 GB vs 4.7 GB).
- **Limitations:**
  - The approach relies on a closed-world assumption.
  - It needs a complete KG schema.
  - Results depend on the backbone LLM.
  - NestKGQA is relatively small.
  - Data and code are available at github.com/midannii/CUCKOO.

*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

- [Yonsei University](https://md.research.elamur.ai/free/en/universities/yonsei-university/) — University, Seoul, South Korea · 18 works · 501 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

## Cite

Cite as: Midan Shim, Seokju Hwang, KaeHyun Um and Kyong-Ho Lee. 2026. Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement. 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{shim2026which,
  title = {{Which bird does not have wings: Negative-constrained KGQA with Schema-guided Semantic Matching and Self-directed Refinement}},
  author = {Midan Shim, Seokju Hwang, KaeHyun Um and Kyong-Ho Lee},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1132},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1132}
}
```

- [← previous Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models](https://md.research.elamur.ai/free/en/papers/yuan-2026-where-paths-split-localized-calibrated/)
- [next → Which Skills Debate Reaches the Public? Comparing Scientific Literature and Media Coverage of AI and LLM Skill Impacts (2022–2025)](https://md.research.elamur.ai/free/en/papers/reveilhac-2026-which-skills-debate-reaches-public/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/56/)

## References

51 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
2. Prerna Agarwal, Nishant Kumar, and Srikanta Bedathur. 2024. Symkgqa: Few-shot knowledge graph question answering via symbolic program generation and execution. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10119–10140. [find](https://scholar.google.com/scholar?q=Prerna+Agarwal%2C+Nishant+Kumar%2C+and+Srikanta+Bedathur%2E+2024%2E+Symkgqa%3A+Few%2Dshot+knowledge+graph+question+answering+via+symbolic+program+generation+and+execution%2E+In+Proceedings+of+the+62nd+Annual+Meetin)
3. Prerna Agarwal, Nishant Kumar, and Srikanta Bedathur Jagannath. 2025. Aligning complex knowledge graph question answering as knowledge-aware constrained code generation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3952–3978. [find](https://scholar.google.com/scholar?q=Prerna+Agarwal%2C+Nishant+Kumar%2C+and+Srikanta+Bedathur+Jagannath%2E+2025%2E+Aligning+complex+knowledge+graph+question+answering+as+knowledge%2Daware+constrained+code+generation%2E+In+Proceedings+of+the+31st+Int)
4. Javier Álvez, Itziar Gonzalez-Dios, and German Rigau. 2020. Applying the closed world assumption to sumo-based fol ontologies for effective commonsense reasoning. In ECAI 2020, pages 585–592. IOS Press. [find](https://scholar.google.com/scholar?q=Javier+%C3%81lvez%2C+Itziar+Gonzalez%2DDios%2C+and+German+Rigau%2E+2020%2E+Applying+the+closed+world+assumption+to+sumo%2Dbased+fol+ontologies+for+effective+commonsense+reasoning%2E+In+ECAI+2020%2C+pages+585%E2%80%93592%2E+IOS+Pres)
5. Farah Atif, Ola El Khatib, and Djellel Difallah. 2023. Beamqa: Multi-hop knowledge graph question answering with sequence-to-sequence prediction and beam search. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 781–790. [find](https://scholar.google.com/scholar?q=Farah+Atif%2C+Ola+El+Khatib%2C+and+Djellel+Difallah%2E+2023%2E+Beamqa%3A+Multi%2Dhop+knowledge+graph+question+answering+with+sequence%2Dto%2Dsequence+prediction+and+beam+search%2E+In+Proceedings+of+the+46th+Internation)
6. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
7. Shulin Cao, Jiaxin Shi, Liangming Pan, Lunyiu Nie, Yutong Xiang, Lei Hou, Juanzi Li, Bin He, and Hanwang Zhang. 2022. Kqa pro: A dataset with explicit compositional programs for complex question answering over knowledge base. In Proceedings of the 60th Annual Meeting of the Association for Computati… [find](https://scholar.google.com/scholar?q=Shulin+Cao%2C+Jiaxin+Shi%2C+Liangming+Pan%2C+Lunyiu+Nie%2C+Yutong+Xiang%2C+Lei+Hou%2C+Juanzi+Li%2C+Bin+He%2C+and+Hanwang+Zhang%2E+2022%2E+Kqa+pro%3A+A+dataset+with+explicit+compositional+programs+for+complex+question+answe)
8. Shengxiang Gao, Jey Han Lau, and Jianzhong Qi. 2025. Beyond seen data: Improving KBQA generalization through schema-guided logical form generation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 8764–8783, Suzhou, China. Association for Computational… [find](https://scholar.google.com/scholar?q=Shengxiang+Gao%2C+Jey+Han+Lau%2C+and+Jianzhong+Qi%2E+2025%2E+Beyond+seen+data%3A+Improving+KBQA+generalization+through+schema%2Dguided+logical+form+generation%2E+In+Proceedings+of+the+2025+Conference+on+Empirical+M)
9. Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. [Simcse: Simple contrastive learning of sentence embeddings](https://md.research.elamur.ai/free/en/papers/gao-2021-simcse-simple-contrastive-learning-sentence/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6894–6910.
10. Iker García-Ferrero, Begoña Altuna, Javier Álvez, Itziar Gonzalez-Dios, and German Rigau. 2023. This is not a dataset: A large negation benchmark to challenge large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8596–8615. [find](https://scholar.google.com/scholar?q=Iker+Garc%C3%ADa%2DFerrero%2C+Bego%C3%B1a+Altuna%2C+Javier+%C3%81lvez%2C+Itziar+Gonzalez%2DDios%2C+and+German+Rigau%2E+2023%2E+This+is+not+a+dataset%3A+A+large+negation+benchmark+to+challenge+large+language+models%2E+In+Proceedings+of+)
11. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
12. Yu Gu, Sue Kase, Michelle Vanni, Brian Sadler, Percy Liang, Xifeng Yan, and Yu Su. 2021. Beyond iid: three levels of generalization for question answering on knowledge bases. In Proceedings of the Web Conference 2021, pages 3477–3488. [find](https://scholar.google.com/scholar?q=Yu+Gu%2C+Sue+Kase%2C+Michelle+Vanni%2C+Brian+Sadler%2C+Percy+Liang%2C+Xifeng+Yan%2C+and+Yu+Su%2E+2021%2E+Beyond+iid%3A+three+levels+of+generalization+for+question+answering+on+knowledge+bases%2E+In+Proceedings+of+the+Web)
13. Yu Gu and Yu Su. 2022. Arcaneqa: Dynamic program induction and contextualized encoding for knowledge base question answering. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1718–1731. [find](https://scholar.google.com/scholar?q=Yu+Gu+and+Yu+Su%2E+2022%2E+Arcaneqa%3A+Dynamic+program+induction+and+contextualized+encoding+for+knowledge+base+question+answering%2E+In+Proceedings+of+the+29th+International+Conference+on+Computational+Lingu)
14. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
15. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2025. [A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/). ACM Transactions on Information Systems, 43(2):…
16. Tianle Li, Xueguang Ma, Alex Zhuang, Yu Gu, Yu Su, and Wenhu Chen. 2023. Few-shot in-context learning on knowledge base question answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6966–6980. [find](https://scholar.google.com/scholar?q=Tianle+Li%2C+Xueguang+Ma%2C+Alex+Zhuang%2C+Yu+Gu%2C+Yu+Su%2C+and+Wenhu+Chen%2E+2023%2E+Few%2Dshot+in%2Dcontext+learning+on+knowledge+base+question+answering%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association)
17. Percy Liang. 2013. Lambda dependency-based compositional semantics. arXiv e-prints, pages arXiv–1309. [find](https://scholar.google.com/scholar?q=Percy+Liang%2E+2013%2E+Lambda+dependency%2Dbased+compositional+semantics%2E+arXiv+e%2Dprints%2C+pages+arXiv%E2%80%931309%2E)
18. Aixin Liu, Bei Feng, Bin Wang, Bingxuan Wang, Bo Liu, Chenggang Zhao, Chengqi Dengr, Chong Ruan, Damai Dai, Daya Guo, et al. 2024. Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model. arXiv preprint arXiv:2405.04434. [find](https://scholar.google.com/scholar?q=Aixin+Liu%2C+Bei+Feng%2C+Bin+Wang%2C+Bingxuan+Wang%2C+Bo+Liu%2C+Chenggang+Zhao%2C+Chengqi+Dengr%2C+Chong+Ruan%2C+Damai+Dai%2C+Daya+Guo%2C+et+al%2E+2024%2E+Deepseek%2Dv2%3A+A+strong%2C+economical%2C+and+efficient+mixture%2Dof%2Dexperts+l)
19. Haoran Luo, E Haihong, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin, et al. 2024a. Chatkbqa: A generate-then-retrieve framework for knowledge base question answering with fine-tuned large language models. In Findings of the Association for Comput… [find](https://scholar.google.com/scholar?q=Haoran+Luo%2C+E+Haihong%2C+Zichen+Tang%2C+Shiyao+Peng%2C+Yikai+Guo%2C+Wentai+Zhang%2C+Chenghao+Ma%2C+Guanting+Dong%2C+Meina+Song%2C+Wei+Lin%2C+et+al%2E+2024a%2E+Chatkbqa%3A+A+generate%2Dthen%2Dretrieve+framework+for+knowledge+base)
20. Linhao Luo, Yuan-Fang Li, Reza Haf, and Shirui Pan. 2024b. Reasoning on graphs: Faithful and interpretable large language model reasoning. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Yuan%2DFang+Li%2C+Reza+Haf%2C+and+Shirui+Pan%2E+2024b%2E+Reasoning+on+graphs%3A+Faithful+and+interpretable+large+language+model+reasoning%2E+In+The+Twelfth+International+Conference+on+Learning+Represent)
21. Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jiajun Zhang, Bowen Yu, Keming Lu, et al. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186. — [Qwen2.5-Coder Technical Report](https://md.research.elamur.ai/free/en/papers/hui-2024-qwen2-5-coder-technical-report/)
22. I Muneeswaran, Advaith Shankar, V Varun, Saisubra-maniam Gopalakrishnan, and Vishal Vaddina. 2024. Mitigating factual inconsistency and hallucination in large language models. In WSDM, pages 1169–1170. [find](https://scholar.google.com/scholar?q=I+Muneeswaran%2C+Advaith+Shankar%2C+V+Varun%2C+Saisubra%2Dmaniam+Gopalakrishnan%2C+and+Vishal+Vaddina%2E+2024%2E+Mitigating+factual+inconsistency+and+hallucination+in+large+language+models%2E+In+WSDM%2C+pages+1169%E2%80%931170)
23. 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. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9237–9251. [find](https://scholar.google.com/scholar?q=Jinhao+Jiang%2C+Kun+Zhou%2C+Zican+Dong%2C+Keming+Ye%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2023%2E+Structgpt%3A+A+general+framework+for+large+language+model+to+reason+over+structured+data%2E+In+Proceedings+of+the+2023)
24. Zhijie Nie, Richong Zhang, Zhongyuan Wang, and Xudong Liu. 2024. Code-style in-context learning for knowledge-based question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18833–18841. [find](https://scholar.google.com/scholar?q=Zhijie+Nie%2C+Richong+Zhang%2C+Zhongyuan+Wang%2C+and+Xudong+Liu%2E+2024%2E+Code%2Dstyle+in%2Dcontext+learning+for+knowledge%2Dbased+question+answering%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence)
25. Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2019. [Billion-scale similarity search with gpus](https://md.research.elamur.ai/free/en/papers/johnson-2017-billion-scale-similarity-search-gpus/). IEEE Transactions on Big Data, 7(3):535–547.
26. Magdalena Kaiser, Rishiraj Saha Roy, and Gerhard Weikum. 2024. Robust training for conversational question answering models with reinforced reformulation generation. In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pages 322–331. [find](https://scholar.google.com/scholar?q=Magdalena+Kaiser%2C+Rishiraj+Saha+Roy%2C+and+Gerhard+Weikum%2E+2024%2E+Robust+training+for+conversational+question+answering+models+with+reinforced+reformulation+generation%2E+In+Proceedings+of+the+17th+ACM+Int)
27. Jean Louis Krivine. 1993. Lambda-calculus, types and models. Ellis Horwood. [find](https://scholar.google.com/scholar?q=Jean+Louis+Krivine%2E+1993%2E+Lambda%2Dcalculus%2C+types+and+models%2E+Ellis+Horwood%2E)
28. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–9474.
29. MohammadHossein Rezaei and Eduardo Blanco. 2024. Paraphrasing in affirmative terms improves negation understanding. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 602–615, Bangkok, Thailand. Association for Computational Lin… [find](https://scholar.google.com/scholar?q=MohammadHossein+Rezaei+and+Eduardo+Blanco%2E+2024%2E+Paraphrasing+in+affirmative+terms+improves+negation+understanding%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Computational+Lingu)
30. Jingyuan S She, Christopher Potts, Samuel Bowman, and Atticus Geiger. 2023. Scone: Benchmarking negation reasoning in language models with fine-tuning and in-context learning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1… [find](https://scholar.google.com/scholar?q=Jingyuan+S+She%2C+Christopher+Potts%2C+Samuel+Bowman%2C+and+Atticus+Geiger%2E+2023%2E+Scone%3A+Benchmarking+negation+reasoning+in+language+models+with+fine%2Dtuning+and+in%2Dcontext+learning%2E+In+Proceedings+of+the+61)
31. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. [Reflexion: Language agents with verbal reinforcement learning](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/). Advances in Neural Information Processing Systems, 36:8634–8652.
32. Yiheng Shu, Zhiwei Yu, Yuhan Li, Börje Karlsson, Tingting Ma, Yuzhong Qu, and Chin-Yew Lin. 2022. Tiara: Multi-grained retrieval for robust question answering over large knowledge base. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8108–8121. [find](https://scholar.google.com/scholar?q=Yiheng+Shu%2C+Zhiwei+Yu%2C+Yuhan+Li%2C+B%C3%B6rje+Karlsson%2C+Tingting+Ma%2C+Yuzhong+Qu%2C+and+Chin%2DYew+Lin%2E+2022%2E+Tiara%3A+Multi%2Dgrained+retrieval+for+robust+question+answering+over+large+knowledge+base%2E+In+Proceedings)
33. Yu Su, Huan Sun, Brian Sadler, Mudhakar Srivatsa, Izzeddin Gür, Zenghui Yan, and Xifeng Yan. 2016. On generating characteristic-rich question sets for qa evaluation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 562–572. [find](https://scholar.google.com/scholar?q=Yu+Su%2C+Huan+Sun%2C+Brian+Sadler%2C+Mudhakar+Srivatsa%2C+Izzeddin+G%C3%BCr%2C+Zenghui+Yan%2C+and+Xifeng+Yan%2E+2016%2E+On+generating+characteristic%2Drich+question+sets+for+qa+evaluation%2E+In+Proceedings+of+the+2016+Confere)
34. Yushi Wang, Jonathan Berant, and Percy Liang. 2015. Building a semantic parser overnight. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1332–1342, Bei… [find](https://scholar.google.com/scholar?q=Yushi+Wang%2C+Jonathan+Berant%2C+and+Percy+Liang%2E+2015%2E+Building+a+semantic+parser+overnight%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+7th+Interna)
35. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 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/). Advances in neural information processing systems, 35:24824–24837.
36. 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. In The Twelfth International Conference on Learning Representations. [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+Ni%2C+Heung%2DYeung+Shum%2C+and+Jian+Guo%2E+2024%2E+Think%2Don%2Dgraph%3A+Deep+and+responsible+reasoning+of+large+language+model+o)
37. Yike Wu, Yi Huang, Nan Hu, Yuncheng Hua, Guilin Qi, Jiaoyan Chen, and Jeff Pan. 2024. Cotkr: Chain-of-thought enhanced knowledge rewriting for complex knowledge graph question answering. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 3501–3520. [find](https://scholar.google.com/scholar?q=Yike+Wu%2C+Yi+Huang%2C+Nan+Hu%2C+Yuncheng+Hua%2C+Guilin+Qi%2C+Jiaoyan+Chen%2C+and+Jeff+Pan%2E+2024%2E+Cotkr%3A+Chain%2Dof%2Dthought+enhanced+knowledge+rewriting+for+complex+knowledge+graph+question+answering%2E+In+Proceeding)
38. Tilahun Abedissa Taffa and Ricardo Usbeck. 2025. Bridge-generate: Scholarly hybrid question answering. In Companion Proceedings of the ACM on Web Conference 2025, pages 1321–1325. [find](https://scholar.google.com/scholar?q=Tilahun+Abedissa+Taffa+and+Ricardo+Usbeck%2E+2025%2E+Bridge%2Dgenerate%3A+Scholarly+hybrid+question+answering%2E+In+Companion+Proceedings+of+the+ACM+on+Web+Conference+2025%2C+pages+1321%E2%80%931325%2E)
39. Guanming Xiong, Junwei Bao, and Wen Zhao. 2024. Interactive-kbqa: Multi-turn interactions for knowledge base question answering with large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10561–10582. [find](https://scholar.google.com/scholar?q=Guanming+Xiong%2C+Junwei+Bao%2C+and+Wen+Zhao%2E+2024%2E+Interactive%2Dkbqa%3A+Multi%2Dturn+interactions+for+knowledge+base+question+answering+with+large+language+models%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of)
40. Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, and Wenjie Zhang. 2025. [Paths-over-graph: Knowledge graph empowered large language model reasoning](https://md.research.elamur.ai/free/en/papers/tan-2024-paths-over-graph-knowledge-graph/). In Proceedings of the ACM on Web Conference 2025, pages 3505–3522.
41. Thinh Hung Truong, Timothy Baldwin, Karin Verspoor, and Trevor Cohn. 2023. [Language models are not naysayers: an analysis of language models on negation benchmarks](https://md.research.elamur.ai/free/en/papers/truong-2023-language-models-naysayers-analysis-language/). In Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023), pages 101–114, Toronto, Canada. Associa…
42. Ricardo Usbeck, Xi Yan, Aleksandr Perevalov, Longquan Jiang, Julius Schulz, Angelie Kraft, Cedric Möller, Junbo Huang, Jan Reineke, Axel-Cyrille Ngonga Ngomo, et al. 2024. Qald-10–the 10th challenge on question answering over linked data: Shifting from dbpedia to wikidata as a kg for kgqa. Semantic… [find](https://scholar.google.com/scholar?q=Ricardo+Usbeck%2C+Xi+Yan%2C+Aleksandr+Perevalov%2C+Longquan+Jiang%2C+Julius+Schulz%2C+Angelie+Kraft%2C+Cedric+M%C3%B6ller%2C+Junbo+Huang%2C+Jan+Reineke%2C+Axel%2DCyrille+Ngonga+Ngomo%2C+et+al%2E+2024%2E+Qald%2D10%E2%80%93the+10th+challenge+o)
43. Neeraj Varshney, Satyam Raj, Venkatesh Mishra, Agneet Chatterjee, Amir Saeidi, Ritika Sarkar, and Chitta Baral. 2025. Investigating and addressing hallucinations of LLMs in tasks involving negation. In Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025), pages 580–598, Albuquerque, Ne… [find](https://scholar.google.com/scholar?q=Neeraj+Varshney%2C+Satyam+Raj%2C+Venkatesh+Mishra%2C+Agneet+Chatterjee%2C+Amir+Saeidi%2C+Ritika+Sarkar%2C+and+Chitta+Baral%2E+2025%2E+Investigating+and+addressing+hallucinations+of+LLMs+in+tasks+involving+negation%2E+I)
44. Fanqi Wan, Xinting Huang, Leyang Cui, Xiaojun Quan, Wei Bi, and Shuming Shi. 2024. Mitigating hallucinations of large language models via knowledge consistent alignment. CoRR. [find](https://scholar.google.com/scholar?q=Fanqi+Wan%2C+Xinting+Huang%2C+Leyang+Cui%2C+Xiaojun+Quan%2C+Wei+Bi%2C+and+Shuming+Shi%2E+2024%2E+Mitigating+hallucinations+of+large+language+models+via+knowledge+consistent+alignment%2E+CoRR%2E)
45. Xingyao Wang, Sha Li, and Heng Ji. 2023. [Code4struct: Code generation for few-shot event structure prediction](https://md.research.elamur.ai/free/en/papers/wang-2023-code4struct-code-generation-few-shot/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3640–3663.
46. Derong Xu, Xinhang Li, Ziheng Zhang, Zhenxi Lin, Zhihong Zhu, Zhi Zheng, Xian Wu, Xiangyu Zhao, Tong Xu, and Enhong Chen. 2025. Harnessing large language models for knowledge graph question answering via adaptive multi-aspect retrieval-augmentation. In Proceedings of the AAAI Conference on Artificia… [find](https://scholar.google.com/scholar?q=Derong+Xu%2C+Xinhang+Li%2C+Ziheng+Zhang%2C+Zhenxi+Lin%2C+Zhihong+Zhu%2C+Zhi+Zheng%2C+Xian+Wu%2C+Xiangyu+Zhao%2C+Tong+Xu%2C+and+Enhong+Chen%2E+2025%2E+Harnessing+large+language+models+for+knowledge+graph+question+answering+)
47. Mengyu Ye, Tatsuki Kuribayashi, Jun Suzuki, Goro Kobayashi, and Hiroaki Funayama. 2023. Assessing step-by-step reasoning against lexical negation: A case study on syllogism. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14753–14773. [find](https://scholar.google.com/scholar?q=Mengyu+Ye%2C+Tatsuki+Kuribayashi%2C+Jun+Suzuki%2C+Goro+Kobayashi%2C+and+Hiroaki+Funayama%2E+2023%2E+Assessing+step%2Dby%2Dstep+reasoning+against+lexical+negation%3A+A+case+study+on+syllogism%2E+In+Proceedings+of+the+2023)
48. Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, and Caiming Xiong. 2022. RNG-KBQA: Generation augmented iterative ranking for knowledge base question answering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6032–6043, Dub… [find](https://scholar.google.com/scholar?q=Xi+Ye%2C+Semih+Yavuz%2C+Kazuma+Hashimoto%2C+Yingbo+Zhou%2C+and+Caiming+Xiong%2E+2022%2E+RNG%2DKBQA%3A+Generation+augmented+iterative+ranking+for+knowledge+base+question+answering%2E+In+Proceedings+of+the+60th+Annual+Me)
49. 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.
50. Donghan Yu, Sheng Zhang, Patrick Ng, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Yiqun Hu, William Yang Wang, Zhiguo Wang, and Bing Xiang. 2023. Decaf: Joint decoding of answers and logical forms for question answering over knowledge bases. In The Eleventh International Conference on Learning Represe… [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+Yang+Wang%2C+Zhiguo+Wang%2C+and+Bing+Xiang%2E+2023%2E+Decaf%3A+Joint+decoding+of+answers+and+logical+forms+for+q)
51. Tianyu Zheng, Ge Zhang, Tianhao Shen, Xueling Liu, Bill Yuchen Lin, Jie Fu, Wenhu Chen, and Xiang Yue. 2024. [Opencodeinterpreter: Integrating code generation with execution and refinement](https://md.research.elamur.ai/free/en/papers/zheng-2024-opencodeinterpreter-integrating-code-generation-execution/). In Findings of the Association for Computational Linguistics ACL 2024, pages 12834–12859. *Figure 6: Prompts fo…

*Updated 2 November 2026*