CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation
Open accessAbstract
Large Language Models (LLMs) have emerged as powerful assistants for scientific writing.However, concerns remain about the quality and reliability of the generated text, including citation accuracy and faithfulness.While most recent work relies on methods such as LLMas-a-Judge, the reliability of LLM-as-a-Judge alone is also in doubt.In this work, we reframe citation evaluation as a problem of citation attribution alignment, which assesses whether LLM-generated citations match those a human author would include for the same text.We propose CiteGuard, a retrieval-aware agent framework designed to provide more faithful grounding for citation validation.CiteGuard improves over the prior baseline by 10 percentage points and achieves up to 68.1% accuracy on the CiteME benchmark, approaching human performance (69.2%).It also identifies alternative valid citations and demonstrates generalization ability for cross-domain citation attribution. 1
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Citation attribution benchmarks such as CiteME and CiteGuard test whether a model attributes a scientific claim to the correct source paper, a matching task over a fixed corpus.
“Citation attribution benchmarks such as CiteME [Press et al., 2024] and CiteGuard [Choi et al., 2026] test whether a model attributes a scientific claim to the correct source paper, a matching task over a fixed corpus.”
From Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution (2026) · cites this paper as Choi et al., 2026
Section 3.1 describes CiteME as a benchmark of 130 excerpts with missing citations and says CiteGuard is an agent evaluated on it. The claim is therefore right about testing citation attribution, but CiteGuard is not itself a benchmark, and the paper does not describe the task as matching papers from a fixed candidate corpus. Section 4.2 also reports that CiteGuard identifies valid citations beyond the original references. (LLM, conf=0.88)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
CiteME: Can Language Models Accurately Cite Scientific Claims?
Press, O., Hochlehnert, A., Prabhu, A., Udandarao, V., Press, O., & Bethge, M. (2024) · arXiv · doi:10.48550/arxiv.2407.12861 · Cited by 4
Flagged first, then by citations
Research works printed but not linked: 31
- Akari Asai, Jacqueline He, Rulin Shao, Weijia Shi, Amanpreet Singh, Joseph Chee Chang, Kyle Lo, Luca Soldaini, Sergey Feldman, Mike D'arcy, David Wadden, Matt Latzke, Minyang Tian, Pan Ji, Shengyan Liu, Hao Tong, Bohao Wu, Yanyu Xiong, Luke Zettlemoyer, and 6 others. 2024. Openscholar: Synthesizing scientific literature with retrieval- augmented lms. Preprint, arXiv:2411.14199. · arXiv
- Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-rag: Learning to retrieve, generate, and critique through self-reflection. Preprint, arXiv:2310.11511. · arXiv
- Sebastian Borgeaud, Arthur Mensch, Jordan Hoff- mann, Trevor Cai, Eliza Rutherford, Katie Milli- can, George Bm Van Den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, Diego De Las Casas, Aurelia Guy, Jacob Menick, Roman Ring, Tom Hennigan, Saffron Huang, Loren Mag- giore, Chris Jones, Albin Cassirer, and 9 others. 2022. Improving language models by retrieving from tril- lions of tokens. In Proceedings of the 39th Interna- tional Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pages 2206-2240. PMLR.
- Lutz Bornmann and Rüdiger Mutz. 2015. Growth rates of modern science: A bibliometric analysis based on the number of publications and cited references. Journal of the Association for Information Science and Technology, 66(11):2215-2222. · DOI · Paper page
- Uchendu Eugene Chigbu, Sulaiman Olusegun Atiku, and Cherley C. Du Plessis. 2023. The science of literature reviews: Searching, identifying, selecting, and synthesising. Publications, 11(1). Google Cloud. 2025. Gemini 2.0 flash. Travis Ebesu and Yi Fang. 2017. Neural citation net- work for context-aware citation recommendation. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Infor- mation Retrieval, SIGIR '17, page 1093-1096, New York, NY, USA. Association for Computing Machin- ery. · DOI
- Zhiyuan Fan, Longfei Yun, Ming Yan, Yumeng Wang, Dadi Guo, Brian Mak, James Kwok, and Yi R. Fung. 2025. End-to-end optimization for multimodal retrieval-augmented generation via reward backprop- agation. In Findings of the Association for Compu- tational Linguistics: EMNLP 2025, pages 443-466, Suzhou, China. Association for Computational Lin- guistics. · DOI
- Michael Färber and Ashwath Sampath. 2020. Hybrid- cite: A hybrid model for context-aware citation rec- ommendation. In Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020, JCDL '20, page 117-126, New York, NY, USA. Association for Computing Machinery. · DOI
- Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Meng Wang, and Haofen Wang. 2024. Retrieval-augmented gener- ation for large language models: A survey. Preprint, arXiv:2312.10997. · arXiv
- Jiawei Gu, Xuhui Jiang, Zhichao Shi, Hexiang Tan, Xuehao Zhai, Chengjin Xu, Wei Li, Yinghan Shen, Shengjie Ma, Honghao Liu, Saizhuo Wang, Kun Zhang, Yuanzhuo Wang, Wen Gao, Lionel Ni, and Jian Guo. 2025. A survey on llm-as-a-judge. Preprint, arXiv:2411.15594. · arXiv
- Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhu- oshu Li, Ziyi Gao, Aixin Liu, and 175 others. 2025. Deepseek-r1 incentivizes reasoning in llms through reinforcement learning. Nature, 645(8081):633-638. · DOI · Paper page
- Qi He, Cheng Qian, Xiusi Chen, Bingxiang He, Yi R. Fung, and Heng Ji. 2025. Veri-r1: Toward precise and faithful claim verification via online reinforce- ment learning. Preprint, arXiv:2510.01932. · arXiv
- Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2025. A survey on hallucination in large lan- guage models: Principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst., 43(2). · DOI · Paper page
- Chanwoo Jeong, Sion Jang, Eunjeong Park, and Sungchul Choi. 2020. A context-aware citation rec- ommendation model with bert and graph convolu- tional networks. Scientometrics, 124(3):1907-1922. · DOI · Paper page
- 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 halluci- nation in natural language generation. ACM Comput. Surv., 55(12). · DOI · Paper page
- Michael Krumdick, Charles Lovering, Varshini Reddy, Seth Ebner, and Chris Tanner. 2026. No free labels: Limitations of llm-as-a-judge without human ground- ing. Preprint, arXiv:2503.05061. · arXiv
- Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Hein- rich Küttler, Mike Lewis, Wen-tau Yih, Tim Rock- täschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge- intensive nlp tasks. In Proceedings of the 34th Inter- national Conference on Neural Information Process- ing Systems, NIPS '20, Red Hook, NY, USA.
- Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foer- ster, Jeff Clune, and David Ha. 2024. The ai scientist: Towards fully automated open-ended scientific dis- covery. Preprint, arXiv:2408.06292. · arXiv
- Jiacheng Miao, Joe R. Davis, Yaohui Zhang, Jonathan K. Pritchard, and James Zou. 2025. Paper2agent: Reimagining research papers as interactive and reli- able ai agents. Preprint, arXiv:2509.06917. · arXiv
- OpenAI, :, Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M ądry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, and 401 others. 2024. Gpt-4o system card. Preprint, arXiv:2410.21276. · arXiv
- G. Salton and D. Bergmark. 1979. A citation study of computer science literature. IEEE Transactions on Professional Communication, PC-22(3):146-158. · DOI
- Hannah Snyder. 2019. Literature review as a research methodology: An overview and guidelines. Journal of Business Research, 104:333-339. · DOI · Paper page
- Kimi Team, Yifan Bai, Yiping Bao, Y. Charles, Cheng Chen, Guanduo Chen, Haiting Chen, Huarong Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, Zhuofu Chen, Jialei Cui, Hao Ding, Mengnan Dong, Angang Du, and 181 others. 2026. Kimi k2: Open agentic intelli- gence. Preprint, arXiv:2507.20534. · arXiv
- Aman Singh Thakur, Kartik Choudhary, Venkat Srinik Ramayapally, Sankaran Vaidyanathan, and Dieuwke Hupkes. 2025. Judging the judges: Evaluating align- ment and vulnerabilities in LLMs-as-judges. In Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM²), pages 404-430, Vi- enna, Austria and virtual meeting. Association for Computational Linguistics.
- Qingyun Wang, Doug Downey, Heng Ji, and Tom Hope. 2024a. SciMON: Scientific inspiration machines optimized for novelty. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 279-299, Bangkok, Thailand. Association for Computational Linguistics. · DOI
- Yidong Wang, Qi Guo, Wenjin Yao, Hongbo Zhang, Xin Zhang, Zhen Wu, Meishan Zhang, Xinyu Dai, Min Zhang, Qingsong Wen, Wei Ye, Shikun Zhang, and Yue Zhang. 2024b. Autosurvey: large language mod- els can automatically write surveys. In Proceedings of the 38th International Conference on Neural In- formation Processing Systems, NIPS '24, Red Hook, NY, USA.
- Yubo Wang, Xueguang Ma, Ping Nie, Huaye Zeng, Zhiheng Lyu, Yuxuan Zhang, Benjamin Schneider, Yi Lu, Xiang Yue, and Wenhu Chen. 2025. Schol- arcopilot: Training large language models for aca- demic writing with accurate citations. Preprint, arXiv:2504.00824. · arXiv
- Yutaro Yamada, Robert Tjarko Lange, Cong Lu, Shen- gran Hu, Chris Lu, Jakob Foerster, Jeff Clune, and David Ha. 2025. The ai scientist-v2: Workshop-level automated scientific discovery via agentic tree search. Preprint, arXiv:2504.08066. · arXiv
- An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Day- iheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. Qwen3 technical report. Preprint, arXiv:2505.09388. · arXiv
- Libin Yang, Yu Zheng, Xiaoyan Cai, Hang Dai, De- jun Mu, Lantian Guo, and Tao Dai. 2018. A lstm based model for personalized context-aware citation recommendation. IEEE Access, 6:59618-59627. · DOI
- Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations.
- Jiayi Ye, Yanbo Wang, Yue Huang, Dongping Chen, Qihui Zhang, Nuno Moniz, Tian Gao, Werner Geyer, Chao Huang, Pin-Yu Chen, Nitesh V Chawla, and Xiangliang Zhang. 2025. Justice or prejudice? quan- tifying biases in LLM-as-a-judge. In The Thirteenth International Conference on Learning Representa- tions.
Cited by
Sorted by citations
Leung, E., Lumer, E., Feld, C., Huber, A., Subbiah, V. K., & Paul, K. (2026) · arXiv · doi:10.48550/arxiv.2607.08700
- Authors
- Choi, Y. M., Guo, X., Fung, Y. R., & Wang, Q.
- Affiliations
- University of Waterloo (CA)
- William & Mary (US)
- University of Illinois Urbana-Champaign (US)
- ORCID
- Guo, Xuehang
- Venue
- Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2026
- Pages
- 6241-6257
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W7166824498
- Cited by
- 1
- References
- 1
- Citations by year
- 2026: 1
- FWCI
- 8.94
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Social Sciences › Safety Research › Academic integrity and plagiarism
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Keywords
- citation attribution, citation validation, large language models, LLM-as-a-judge, citation grounding, scientific writing, domain generalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
