---
title: "Reducing Hallucinations in Language Model-based SPARQL"
description: "The authors propose PGMR (Post-Generation Memory Retrieval), which moves retrieval to after… 42 references, cited by 2 papers here."
authors: ["Aditya Sharma", "Christopher Pal", "Amal Zouaq"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: EACL 2026"
source: "https://aclanthology.org/2026.findings-eacl.243/"
doi: "10.18653/v1/2026.findings-eacl.243"
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/sharma-2026-reducing-hallucinations-language-model-based/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sharma-2026-reducing-hallucinations-language-model-based/)

[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/4/) / Reducing Hallucinations in Language Model-based SPARQL Query Generation Using Post-Generation Memory Retrieval

# Reducing Hallucinations in Language Model-based SPARQL Query Generation Using Post-Generation Memory Retrieval

**Authors:** Aditya Sharma, [Christopher Pal](https://md.research.elamur.ai/free/en/authors/christopher-pal/) and Amal Zouaq · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: EACL 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-eacl.243/) · [PDF](https://aclanthology.org/2026.findings-eacl.243.pdf) · [DOI 10.18653/v1/2026.findings-eacl.243](https://doi.org/10.18653/v1/2026.findings-eacl.243) · [OpenAlex](https://openalex.org/W7140130349)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · 2 in our library, of the 149,439 papers whose bibliographies we read

## Summary
LLMs that turn natural-language questions into SPARQL for Wikidata often invent identifiers. Wikidata URIs such as Q- and P-ids carry no meaning, so the model has to recall them from parametric memory, and it frequently produces IDs that look plausible but are wrong or do not exist. The authors propose PGMR (Post-Generation Memory Retrieval), which moves retrieval to after generation instead of before it, as in RAG. The LLM first writes an intermediate query that keeps full SPARQL syntax but uses tagged natural-language placeholders for entities and relations, each with a label and short description. A non-parametric retriever then matches every placeholder against entity and ontology memories built from KG metadata and substitutes the real URI. Because the placeholder text mirrors the stored metadata, retrieval aligns better than question-based RAG lookup. Tested on untagged LC-QuAD 2.0 and QALD-10 with several LLMs and distribution shifts, PGMR improves semantic query match (SQM) and answer F1 and almost entirely removes hallucinated URIs. It can also decline unanswerable questions and adds very little latency.

## Key points
- The intermediate query wraps placeholders in [ENT]/[REL] tags. Grounding uses separate entity and ontology memories, and every final URI is guaranteed to exist in the KG.
- **Answer refusal:** if any required URI's top retrieval score falls below a confidence threshold, PGMR declines to answer, with no extra training. On LC-QuAD 2.0 with Llama 3.1 8B, a threshold of about 0.85 best balances refusal accuracy against SQM.
- **Memory robustness:** filling the entity memory with up to 9× irrelevant Wikidata distractors lowers SQM by only about 4% (Llama 3.1 8B, LC-QuAD 2.0).
- **Latency:** each retrieval takes about 0.0016 s and needs roughly 600MB of GPU memory, compared with about 0.9 s per LLM generation. The overhead therefore stays negligible even with one lookup per URI.
- **Limitation:** gains are smaller on QALD-10, where complex query structures and literals still trip up the LLM. Code and data are available at github.com/Lama-West/PGMR.

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

📚 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): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) · 192 works

## Cite

Cite as: Aditya Sharma, Christopher Pal and Amal Zouaq. 2026. Reducing Hallucinations in Language Model-based SPARQL Query Generation Using Post-Generation Memory Retrieval. Findings of the Association for Computational Linguistics: EACL 2026.

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

```bibtex
@inproceedings{sharma2026reducing,
  title = {{Reducing Hallucinations in Language Model-based SPARQL Query Generation Using Post-Generation Memory Retrieval}},
  author = {Aditya Sharma, Christopher Pal and Amal Zouaq},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.243},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.243}
}
```

- [← previous Paramanu: Compact and Competitive Monolingual Language Models for Low-Resource Morphologically Rich Indian Languages](https://md.research.elamur.ai/free/en/papers/niyogi-2026-paramanu-compact-competitive-monolingual-language/)
- [next → Report on the BEA 2026 Shared Task on Rubric-based Short Answer Scoring for German](https://md.research.elamur.ai/free/en/papers/gombert-2026-report-bea-2026-shared-task/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/4/)

## References

42 references, 21 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. Debayan Banerjee, Pranav Ajit Nair, Jivat Neet Kaur, Ricardo Usbeck, and Chris Biemann. 2022. Modern baselines for sparql semantic parsing. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2260–2265. [find](https://scholar.google.com/scholar?q=Debayan+Banerjee%2C+Pranav+Ajit+Nair%2C+Jivat+Neet+Kaur%2C+Ricardo+Usbeck%2C+and+Chris+Biemann%2E+2022%2E+Modern+baselines+for+sparql+semantic+parsing%2E+In+Proceedings+of+the+45th+International+ACM+SIGIR+Conferenc)
3. Scott Barnett, Stefanus Kurniawan, Srikanth Thudumu, Zach Brannelly, and Mohamed Abdelrazek. 2024. Seven failure points when engineering a retrieval augmented generation system. In Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering-Software Engineering for AI, pages 194– 199. [find](https://scholar.google.com/scholar?q=Scott+Barnett%2C+Stefanus+Kurniawan%2C+Srikanth+Thudumu%2C+Zach+Brannelly%2C+and+Mohamed+Abdelrazek%2E+2024%2E+Seven+failure+points+when+engineering+a+retrieval+augmented+generation+system%2E+In+Proceedings+of+the+)
4. Felix Brei, Johannes Frey, and Lars-Peter Meyer. 2024. Leveraging small language models for text2sparql tasks to improve the resilience of ai assistance. arXiv preprint arXiv:2405.17076. [find](https://scholar.google.com/scholar?q=Felix+Brei%2C+Johannes+Frey%2C+and+Lars%2DPeter+Meyer%2E+2024%2E+Leveraging+small+language+models+for+text2sparql+tasks+to+improve+the+resilience+of+ai+assistance%2E+arXiv+preprint+arXiv%3A2405%2E17076%2E)
5. 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](https://md.research.elamur.ai/free/en/papers/chen-2024-m3-embedding-multi-linguality/). arXiv preprint arXiv:2402.03216.
6. I Chern, Steffi Chern, Shiqi Chen, Weizhe Yuan, Kehua Feng, Chunting Zhou, Junxian He, Graham Neubig, Pengfei Liu, et al. 2023. [Factool: Factuality detection in generative ai–a tool augmented framework for multi-task and multi-domain scenarios](https://md.research.elamur.ai/free/en/papers/chern-2023-factool-factuality-detection-generative-ai/). arXiv preprint arXiv:2307.13528.
7. Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, and Jason Weston. 2023. [Chain-of-verification reduces hallucination in large language models](https://md.research.elamur.ai/free/en/papers/dhuliawala-2023-chain-verification-reduces-hallucination-large/). arXiv preprint arXiv:2309.11495.
8. Papa Abdou Karim Karou Diallo, Samuel Reyd, and Amal Zouaq. 2024. A comprehensive evaluation of neural sparql query generation from natural language questions. IEEE Access. [find](https://scholar.google.com/scholar?q=Papa+Abdou+Karim+Karou+Diallo%2C+Samuel+Reyd%2C+and+Amal+Zouaq%2E+2024%2E+A+comprehensive+evaluation+of+neural+sparql+query+generation+from+natural+language+questions%2E+IEEE+Access%2E)
9. Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazaré, Maria Lomeli, Lucas Hosseini, and Hervé Jégou. 2024. [The faiss library](https://md.research.elamur.ai/free/en/papers/douze-2024-faiss-library/).
10. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, 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.
11. Mohnish Dubey, Debayan Banerjee, Abdelrahman Abdelkawi, and Jens Lehmann. 2019. Lc-quad 2.0: A large dataset for complex question answering over wikidata and dbpedia. In The Semantic Web–ISWC 2019: 18th International Semantic Web Conference, Auckland, New Zealand, October 26–30, 2019, Proceedings, P… [find](https://scholar.google.com/scholar?q=Mohnish+Dubey%2C+Debayan+Banerjee%2C+Abdelrahman+Abdelkawi%2C+and+Jens+Lehmann%2E+2019%2E+Lc%2Dquad+2%2E0%3A+A+large+dataset+for+complex+question+answering+over+wikidata+and+dbpedia%2E+In+The+Semantic+Web%E2%80%93ISWC+2019%3A+18)
12. Vincent Emonet, Jerven Bolleman, Severine Duvaud, Tarcisio Mendes de Farias, and Ana Claudia Sima. 2024. Llm-based sparql query generation from natural language over federated knowledge graphs. arXiv preprint arXiv:2410.06062. — [arXiv:2410.06062](https://arxiv.org/abs/2410.06062) [find](https://scholar.google.com/scholar?q=Vincent+Emonet%2C+Jerven+Bolleman%2C+Severine+Duvaud%2C+Tarcisio+Mendes+de+Farias%2C+and+Ana+Claudia+Sima%2E+2024%2E+Llm%2Dbased+sparql+query+generation+from+natural+language+over+federated+knowledge+graphs%2E+arXiv+)
13. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. [Retrieval augmented language model pre-training](https://md.research.elamur.ai/free/en/papers/guu-2020-realm-retrieval-augmented-language-model/). In International conference on machine learning, pages 3929–3938. PMLR.
14. Chenxu Hu, Jie Fu, Chenzhuang Du, Simian Luo, Junbo Zhao, and Hang Zhao. 2023. Chatdb: Augmenting llms with databases as their symbolic memory. arXiv preprint arXiv:2306.03901. — [arXiv:2306.03901](https://arxiv.org/abs/2306.03901) [find](https://scholar.google.com/scholar?q=Chenxu+Hu%2C+Jie+Fu%2C+Chenzhuang+Du%2C+Simian+Luo%2C+Junbo+Zhao%2C+and+Hang+Zhao%2E+2023%2E+Chatdb%3A+Augmenting+llms+with+databases+as+their+symbolic+memory%2E+arXiv+preprint+arXiv%3A2306%2E03901%2E+%E2%80%94+%5BarXiv%3A2306%2E03901%5D%28ht)
15. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2023. [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/). arXiv preprint arXiv:2311.05232.
16. Yichong Huang, Xiachong Feng, Xiaocheng Feng, and Bing Qin. 2021. The factual inconsistency problem in abstractive text summarization: A survey. arXiv preprint arXiv:2104.14839. — [arXiv:2104.14839](https://arxiv.org/abs/2104.14839) [find](https://scholar.google.com/scholar?q=Yichong+Huang%2C+Xiachong+Feng%2C+Xiaocheng+Feng%2C+and+Bing+Qin%2E+2021%2E+The+factual+inconsistency+problem+in+abstractive+text+summarization%3A+A+survey%2E+arXiv+preprint+arXiv%3A2104%2E14839%2E+%E2%80%94+%5BarXiv%3A2104%2E14839%5D%28h)
17. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. [Survey of hallucination in natural language generation](https://md.research.elamur.ai/free/en/papers/ji-2022-survey-hallucination-natural-language-generation/). ACM Computing Surveys, 55(12):1–38.
18. 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.
19. Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of NAACL-HLT, pages 4171–4186.
20. Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2019. Generalization through memorization: Nearest neighbor language models. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Urvashi+Khandelwal%2C+Omer+Levy%2C+Dan+Jurafsky%2C+Luke+Zettlemoyer%2C+and+Mike+Lewis%2E+2019%2E+Generalization+through+memorization%3A+Nearest+neighbor+language+models%2E+In+International+Conference+on+Learning+Repr)
21. Yunshi Lan, Gaole He, Jinhao Jiang, Jing Jiang, Wayne Xin Zhao, and Ji-Rong Wen. 2021. A survey on complex knowledge base question answering: Methods, challenges and solutions. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. International Joint Conferences… [find](https://scholar.google.com/scholar?q=Yunshi+Lan%2C+Gaole+He%2C+Jinhao+Jiang%2C+Jing+Jiang%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2021%2E+A+survey+on+complex+knowledge+base+question+answering%3A+Methods%2C+challenges+and+solutions%2E+In+Proceedings+of+the+T)
22. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020a. [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.
23. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020b. [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.
24. Junyi Li, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen. 2023. [Halueval: A large-scale hallucination evaluation benchmark for large language models](https://md.research.elamur.ai/free/en/papers/li-2023-halueval-large-scale-hallucination-evaluation/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6449–6464.
25. Zichao Lin, Shuyan Guan, Wending Zhang, Huiyan Zhang, Yugang Li, and Huaping Zhang. 2024. Towards trustworthy llms: a review on debiasing and dehallucinating in large language models. Artificial Intelligence Review, 57(9):243. [find](https://scholar.google.com/scholar?q=Zichao+Lin%2C+Shuyan+Guan%2C+Wending+Zhang%2C+Huiyan+Zhang%2C+Yugang+Li%2C+and+Huaping+Zhang%2E+2024%2E+Towards+trustworthy+llms%3A+a+review+on+debiasing+and+dehallucinating+in+large+language+models%2E+Artificial+Intel)
26. Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, Sayak Paul, and Benjamin Bossan. 2022. PEFT: State-of-the-art parameter-efficient fine-tuning methods. [https://github.com/huggingface/peft](https://github.com/huggingface/peft). [↗](https://github.com/huggingface/peft)
27. Lars-Peter Meyer, Johannes Frey, Felix Brei, and Natanael Arndt. 2024. Assessing sparql capabilities of large language models. arXiv preprint arXiv:2409.05925. — [arXiv:2409.05925](https://arxiv.org/abs/2409.05925) [find](https://scholar.google.com/scholar?q=Lars%2DPeter+Meyer%2C+Johannes+Frey%2C+Felix+Brei%2C+and+Natanael+Arndt%2E+2024%2E+Assessing+sparql+capabilities+of+large+language+models%2E+arXiv+preprint+arXiv%3A2409%2E05925%2E+%E2%80%94+%5BarXiv%3A2409%2E05925%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
28. Ali Modarressi, Ayyoob Imani, Mohsen Fayyaz, and Hinrich Schütze. 2023. Ret-llm: Towards a general read-write memory for large language models. arXiv preprint arXiv:2305.14322. — [arXiv:2305.14322](https://arxiv.org/abs/2305.14322) [find](https://scholar.google.com/scholar?q=Ali+Modarressi%2C+Ayyoob+Imani%2C+Mohsen+Fayyaz%2C+and+Hinrich+Sch%C3%BCtze%2E+2023%2E+Ret%2Dllm%3A+Towards+a+general+read%2Dwrite+memory+for+large+language+models%2E+arXiv+preprint+arXiv%3A2305%2E14322%2E+%E2%80%94+%5BarXiv%3A2305%2E14322%5D%28ht)
29. Ali Modarressi, Abdullatif Köksal, Ayyoob Imani, Mohsen Fayyaz, and Hinrich Schütze. 2024. Mem-llm: Finetuning llms to use an explicit read-write memory. arXiv preprint arXiv:2404.11672. — [arXiv:2404.11672](https://arxiv.org/abs/2404.11672) [find](https://scholar.google.com/scholar?q=Ali+Modarressi%2C+Abdullatif+K%C3%B6ksal%2C+Ayyoob+Imani%2C+Mohsen+Fayyaz%2C+and+Hinrich+Sch%C3%BCtze%2E+2024%2E+Mem%2Dllm%3A+Finetuning+llms+to+use+an+explicit+read%2Dwrite+memory%2E+arXiv+preprint+arXiv%3A2404%2E11672%2E+%E2%80%94+%5BarXiv%3A2404)
30. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
31. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+O%E2%80%99Brien%2C+Carrie+Jun+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S+Bernstein%2E+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+Proceedings+of+the+36)
32. Ciyuan Peng, Feng Xia, Mehdi Naseriparsa, and Francesco Osborne. 2023. Knowledge graphs: Opportunities and challenges. Artificial Intelligence Review, 56(11):13071–13102. [find](https://scholar.google.com/scholar?q=Ciyuan+Peng%2C+Feng+Xia%2C+Mehdi+Naseriparsa%2C+and+Francesco+Osborne%2E+2023%2E+Knowledge+graphs%3A+Opportunities+and+challenges%2E+Artificial+Intelligence+Review%2C+56%2811%29%3A13071%E2%80%9313102%2E)
33. Jiexing Qi, Chang Su, Zhixin Guo, Lyuwen Wu, Zanwei Shen, Luoyi Fu, Xinbing Wang, and Chenghu Zhou. 2024. Enhancing sparql query generation for knowledge base question answering systems by learning to correct triplets. Applied Sciences, 14(4):1521. [find](https://scholar.google.com/scholar?q=Jiexing+Qi%2C+Chang+Su%2C+Zhixin+Guo%2C+Lyuwen+Wu%2C+Zanwei+Shen%2C+Luoyi+Fu%2C+Xinbing+Wang%2C+and+Chenghu+Zhou%2E+2024%2E+Enhancing+sparql+query+generation+for+knowledge+base+question+answering+systems+by+learning+to)
34. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of machine learning research, 21(140):1–67.
35. Samuel Reyd and Amal Zouaq. 2023. Assessing the generalization capabilities of neural machine translation models for sparql query generation. In International Semantic Web Conference, pages 484–501. Springer. [find](https://scholar.google.com/scholar?q=Samuel+Reyd+and+Amal+Zouaq%2E+2023%2E+Assessing+the+generalization+capabilities+of+neural+machine+translation+models+for+sparql+query+generation%2E+In+International+Semantic+Web+Conference%2C+pages+484%E2%80%93501%2E+S)
36. 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.
37. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2024. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). Advances in Neural Information Processing Systems, 36.
38. Ricardo Usbeck, Xi Yan, Aleksandr Perevalov, Longquan Jiang, Julius Schulz, Angelie Kraft, Cedric Möller, Junbo Huang, Jan Reineke, Axel-Cyrille Ngonga Ngomo, et al. 2023. Qald-10–the 10th challenge on question answering over linked data. Semantic Web, (Preprint):1–15. [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+2023%2E+Qald%2D10%E2%80%93the+10th+challenge+o)
39. Neeraj Varshney, Wenlin Yao, Hongming Zhang, Jianshu Chen, and Dong Yu. 2023. [A stitch in time saves nine: Detecting and mitigating hallucinations of llms by validating low-confidence generation](https://md.research.elamur.ai/free/en/papers/varshney-2023-stitch-time-saves-nine-detecting/). arXiv preprint arXiv:2307.03987.
40. 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.
41. Hamada M Zahera, Manzoor Ali, Mohamed Ahmed Sherif, Diego Moussallem, and Axel-Cyrille Ngonga Ngomo. 2024. Generating sparql from natural language using chain-of-thoughts prompting. In SE-MANTICS, pages 353–368. [find](https://scholar.google.com/scholar?q=Hamada+M+Zahera%2C+Manzoor+Ali%2C+Mohamed+Ahmed+Sherif%2C+Diego+Moussallem%2C+and+Axel%2DCyrille+Ngonga+Ngomo%2E+2024%2E+Generating+sparql+from+natural+language+using+chain%2Dof%2Dthoughts+prompting%2E+In+SE%2DMANTICS%2C+pag)
42. Wangchunshu Zhou, Yuchen Eleanor Jiang, Peng Cui, Tiannan Wang, Zhenxin Xiao, Yifan Hou, Ryan Cotterell, and Mrinmaya Sachan. 2023. [Recurrentgpt: Interactive generation of (arbitrarily) long text](https://md.research.elamur.ai/free/en/papers/zhou-2023-recurrentgpt-interactive-generation-arbitrarily-long/). arXiv preprint arXiv:2305.13304.

*Updated 31 October 2026*