Elamur Research⌕
☰
home / papers / 2026 / JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation

JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation

Paper · 2026 · Fan Xu, Huixuan Zhang, Zhenliang Zhang et al.

Summary

The paper targets factual hallucination detection in open-domain question answering. Retrieval-based checking pipelines usually split an answer into claims, write search queries, gather evidence and then verify each claim. The authors argue that the first two steps are weak: claims lose their context, and queries are too vague to retrieve useful evidence. JointCQ replaces both steps with one finetuned model that outputs claims together with matching search queries in a single pass.

To train this model, the authors build synthetic data. Several open LLMs answer questions from ANAH-v2. Qwen3-32B then extracts claims and drafts a query for each claim. A dual filter keeps only good pairs: claims are checked for entailment, coverage and decontextualization, and queries for relevance, conciseness and usability.

In the full pipeline, the queries go to Google Search, and a Qwen3-14B verifier labels each claim using the retrieved snippets. The system beats strong baselines on several English and Chinese benchmarks. It relies only on open-source models, which keeps cost low and makes deployment easier.

Key points

  • Training data: questions come from ANAH-v2. Answers were produced by Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, gemma-3-4b-it and glm-4-9b-chat.
  • Synthesis setup: claims and queries were generated by Qwen3-32B with 3-shot prompts. For claims, the examples were chosen by semantic similarity (paraphrase-multilingual-mpnet-base-v2) and by answer length.
  • Labels: each claim is tagged as Correct, Hallucinated or Unverifiable. Evidence is the top-10 Google snippets retrieved through the Serper API, and the retrieval component can be swapped for other search engines or local corpora.
  • Comparison with prior work: unlike FacTool and HaluAgent, which call closed-source APIs, JointCQ uses only open models. The authors also report that FacTool is more computationally expensive.
  • Limitations: the method is designed mainly for open-domain QA and depends on Google Search. Code is available at github.com/pku0xff/JointCQ.

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

🎓Peking UniversityBeijing · China315 works · 43,268 citations🏢Huawei TechnologiesShenzhen · China96 works · 15,432 citations

 Fields, topics and concepts

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksSocial Sciences · 1,954 worksInformation Systems · 1,730 worksSociology and Political Science · 626 works

Cite

Cite as Fan Xu, Huixuan Zhang, Zhenliang Zhang, Jiahao Wang and Xiaojun Wan. 2026. JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.58

@inproceedings{xu2026jointcq,
  title = {{JointCQ: Improving Factual Hallucination Detection with Joint Claim and Query Generation}},
  author = {Fan Xu, Huixuan Zhang, Zhenliang Zhang, Jiahao Wang and Xiaojun Wan},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.58},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.58}
}

References

41 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Shayan Ali Akbar, Md Mosharaf Hossain, Tess Wood, Si-Chi Chin, Erica M Salinas, Victor Alvarez, and Erwin Cornejo. 2024. HalluMeasure: Fine-grained hallucination measurement using chain-of-thought reasoning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, p… find
  2. Amos Azaria and Tom Mitchell. 2023. The internal state of an LLM knows when it’s lying. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 967–976, Singapore. Association for Computational Linguistics.
  3. Qinyuan Cheng, Tianxiang Sun, Wenwei Zhang, Siyin Wang, Xiangyang Liu, Mozhi Zhang, Junliang He, Mianqiu Huang, Zhangyue Yin, Kai Chen, and 1 others. 2023. Evaluating hallucinations in chinese large language models. arXiv preprint arXiv:2310.03368. — [arXiv:2310.03368](https://arxiv.org/abs/2310.03368) find
  4. Xiaoxue Cheng, Junyi Li, Xin Zhao, Hongzhi Zhang, Fuzheng Zhang, Di Zhang, Kun Gai, and Ji-Rong Wen. 2024. Small agent can also rock! empowering small language models as hallucination detector. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14600–146… find
  5. I Chern, Steffi Chern, Shiqi Chen, Weizhe Yuan, Kehua Feng, Chunting Zhou, Junxian He, Graham Neubig, Pengfei Liu, and 1 others. 2023. Factool: Factuality detection in generative ai–a tool augmented framework for multi-task and multi-domain scenarios. arXiv preprint arXiv:2307.13528.
  6. Eunsol Choi, Jennimaria Palomaki, Matthew Lamm, Tom Kwiatkowski, Dipanjan Das, and Michael Collins. 2021. Decontextualization: Making sentences stand-alone. Transactions of the Association for Computational Linguistics, 9:447–461.
  7. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, and 3416 other…
  8. DeepSeek-AI. 2024. Deepseek-v3 technical report. Preprint, arXiv:2412.19437. find
  9. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. Deepseek-r1: Incentivizing reasoning capability in ll…
  10. Mohamed Elaraby, Mengyin Lu, Jacob Dunn, Xueying Zhang, Yu Wang, Shizhu Liu, Pingchuan Tian, Yuping Wang, and Yuxuan Wang. 2023. Halo: Estimation and reduction of hallucinations in open-source weak large language models. arXiv preprint arXiv:2308.11764.
  11. Farima Fatahi Bayat, Kun Qian, Benjamin Han, Yisi Sang, Anton Belyy, Samira Khorshidi, Fei Wu, Ihab Ilyas, and Yunyao Li. 2023. FLEEK: Factual error detection and correction with evidence retrieved from external knowledge. In Proceedings of the 2023 Conference on Empirical Methods in Natural Languag… find
  12. Team GLM, :, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, Hanyu Lai, Hao Yu, Hongning Wang, Jiadai Sun, Jiajie Zhang, Jiale Cheng, Jiayi Gui, Jie Tang, and 40 others. 2024. Chatglm: A family of large language models from glm-130b to glm-4 a…
  13. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  14. Yuzhe Gu, Ziwei Ji, Wenwei Zhang, Chengqi Lyu, Dahua Lin, and Kai Chen. 2024. Anah-v2: Scaling analytical hallucination annotation of large language models. Advances in Neural Information Processing Systems, 37:60012–60039. find
  15. Steve Cronen-Townsend, Yun Zhou, and W Bruce Croft. 2002. Predicting query performance. In Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval, pages 299–306. find
  16. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and 1 others. 2023. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems.
  17. Matthew Dahl, Varun Magesh, Mirac Suzgun, and Daniel E Ho. 2024. Large legal fictions: Profiling legal hallucinations in large language models. Journal of Legal Analysis, 16(1):64–93.
  18. Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong Park. 2024. Adaptive-RAG: Learning to adapt retrieval-augmented large language models through question complexity. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Hu…
  19. Ziwei Ji, Yuzhe Gu, Wenwei Zhang, Chengqi Lyu, Dahua Lin, and Kai Chen. 2024. ANAH: Analytical annotation of hallucinations in large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8135–8158, Bangkok, Thailand… find
  20. 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. ACM Computing Surveys, 55(12):1–38.
  21. Ehsan Kamalloo, Nouha Dziri, Charles Clarke, and Davood Rafiei. 2023. Evaluating open-domain question answering in the era of large language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5591–5606, Toronto, Canada. A…
  22. Potsawee Manakul, Adian Liusie, and Mark Gales. 2023. SelfCheckGPT: Zero-resource black-box hallucination detection for generative large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9004–9017, Singapore. Association for Computation… find
  23. Dasha Metropolitansky and Jonathan Larson. 2025. Towards effective extraction and evaluation of factual claims. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6996–7045, Vienna, Austria. Association for Computational Linguist…
  24. Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, and 262 others. 2024. Gpt-4 technical report. Preprint, arXiv:2303.08774.
  25. Ankit Pal, Logesh Kumar Umapathi, and Malaikannan Sankarasubbu. 2023. Med-HALT: Medical domain hallucination test for large language models. In Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), pages 314– 334, Singapore. Association for Computational Linguistics.
  26. Yuehan Qin, Shawn Li, Yi Nian, Xinyan Velocity Yu, Yue Zhao, and Xuezhe Ma. 2025. Don’t let it hallucinate: Premise verification via retrieval-augmented logical reasoning. arXiv preprint arXiv:2504.06438. find
  27. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  28. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
  29. Albert Sawczyn, Jakub Binkowski, Denis Janiak, Bogdan Gabrys, and Tomasz Kajdanowicz. 2025. Fact-selfcheck: Fact-level black-box hallucination detection for llms. arXiv preprint arXiv:2503.17229. — [arXiv:2503.17229](https://arxiv.org/abs/2503.17229) find
  30. Hinrich Schütze, Christopher D Manning, and Prabhakar Raghavan. 2008. Introduction to information retrieval, volume 39. Cambridge University Press Cambridge. find
  31. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. FActScore: Fine-grained atomic evaluation of factual precision in long form text generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural L…
  32. Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, Akshay Nathan, Alan Luo, Alec Helyar, Aleksander Madry, Aleksandr Efremov, Aleksandra Spyra, Alex Baker-Whitcomb, Alex Beutel, Alex Karpenko, and 465 others. 2025… — OpenAI GPT-5 System Card
  33. Jingwei Ni, Minjing Shi, Dominik Stammbach, Mrinmaya Sachan, Elliott Ash, and Markus Leippold. 2024. AFaCTA: Assisting the annotation of factual claim detection with reliable LLM annotators. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pa… find
  34. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penche… find
  35. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Herbert Ullrich, Tomáš Mlynář, and Jan Drchal. 2025. Claim extraction for fact-checking: Data, models, an… — [arXiv:2502.04955](https://arxiv.org/abs/2502.04955) find
  36. Miriam Wanner, Seth Ebner, Zhengping Jiang, Mark Dredze, and Benjamin Van Durme. 2024. A closer look at claim decomposition. In Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024), pages 153–175, Mexico City, Mexico. Association for Computational Linguistics. find
  37. Jerry Wei, Chengrun Yang, Xinying Song, Yifeng Lu, Nathan Hu, Jie Huang, Dustin Tran, Daiyi Peng, Ruibo Liu, Da Huang, and 1 others. 2024. Long-form factuality in large language models. Advances in Neural Information Processing Systems, 37:80756– 80827.
  38. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  39. Jiawei Zhang, Chejian Xu, Yu Gai, Freddy Lecue, Dawn Song, and Bo Li. 2024. Knowhalu: Hallucination detection via multi-form knowledge based factual checking. arXiv preprint arXiv:2404.02935. — [arXiv:2404.02935](https://arxiv.org/abs/2404.02935) find
  40. Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, and Luoyi Fu. 2023a. Enhancing uncertainty-based hallucination detection with stronger focus. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 915–932,… find
  41. Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, and 1 others. 2023b. Siren’s song in the ai ocean: a survey on hallucination in large language models. arXiv preprint arXiv:2309.01219.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xu-2026-jointcq-improving-factual-hallucination-detection/