R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’
Open accessAbstract
Hanning Zhang, Shizhe Diao, Yong Lin, Yi Fung, Qing Lian, Xingyao Wang, Yangyi Chen, Heng Ji, Tong Zhang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
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?
Training with demonstrations of out-of-domain, adversarial, or nonsensical prompts enables a model to generate an "I don't know" response.
“In such cases, it is crucial to train the model to generate an “I don't know” response by including demonstrations of such scenarios in the tuning set [29,130].”
From Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey) (2024) · cites this paper as [130]
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
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 9
- Qingxiu Dong, Jingjing Xu, Lingpeng Kong, Zhifang Sui, and Lei Li. 2023. Statistical knowledge assess- ment for large language models. In Thirty-seventh Conference on Neural Information Processing Sys- tems.
- Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Wein- berger. 2017. On calibration of modern neural net- works. In International conference on machine learn- ing, pages 1321-1330. PMLR.
- 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- ing Surveys, 55(12):1-38.
- Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, and Colin Raffel. 2023. Large language models struggle to learn long-tail knowledge. In In- ternational Conference on Machine Learning, pages 15696-15707.
- PMLR.
- Adam Livska, Tom'avs Kovcisk'y, Elena Gribovskaya, Tayfun Terzi, Eren Sezener, Devang Agrawal, Cy- prien de Masson d'Autume, Tim Scholtes, Manzil Zaheer, Susannah Young, Ellen Gilsenan-McMahon, Sophia Austin, Phil Blunsom, and Angeliki Lazari- dou. 2022. Streamingqa: A benchmark for adapta- tion to new knowledge over time in question answer- ing models. In International Conference on Machine Learning.
- Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. 2022. Emergent abilities of large language models. Transactions on Machine Learning Research.
- Muru Zhang, Ofir Press, William Merrill, Alisa Liu, and Noah A. Smith. 2023a. How language model hallucinations can snowball.
- Model R-Tuning-U acc. R-Tuning-U conf. Vanilla-C acc. Vanilla-C conf. ParaRel ID OpenLLaMA-3B 61.57 61.50 59.81 75.01 LLaMA-7B 65.26 71.25 62.68 77.35 LLaMA-13B 70.47 77.15 65.76 78.50 OOD OpenLLaMA-3B 38.39 43.88 37.66 61.56 LLaMA-7B 42.97 56.00 42.12 63.41 LLaMA-13B 48.40 61.25 40.77 61.20 MMLU ID OpenLLaMA-3B 23.25 44.33 25.54 46.23 LLaMA-7B 41.86 51.06 34.65 53.64 LLaMA-13B 41.90 53.87 39.57 58.60 OOD OpenLLaMA-3B 25.01 41.97 23.81 44.77 LLaMA-7B 45.88 55.22 42.66 58.52 LLaMA-13B 51.74 59.45 50.38 65.53 Table 14: Performance of R-Tuning-U compared with Vanilla-C on the ParaRel and MMLU datasets. ID and OOD denote in-domain and out-of-domain, respectively. Dataset Domain Model R-Tuning-U Vanilla-C ParaRel ID OpenLLaMA-3B 49.96 49.93 LLaMA-7B 50.02 48.80 LLaMA-13B 59.56 59.28 OOD OpenLLaMA-3B 52.26 52.16 LLaMA-7B 49.45 48.52 LLaMA-13B 61.21 61.10 MMLU ID OpenLLaMA-3B 45.01 44.88 LLaMA-7B 50.97 50.95 LLaMA-13B 44.65 43.12 OOD OpenLLaMA-3B 43.10 42.98 LLaMA-7B 58.34 58.33 LLaMA-13B 64.13 62.37
Cited by
Sorted by citations
Epistemic Injustice in Generative AI
Kay, J., Kasirzadeh, A., & Mohamed, S. (2024) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1609/aies.v7i1.31671 · Cited by 76 · see citing works
Know Your Limits: A Survey of Abstention in Large Language Models
Wen, B., Yao, J., Feng, S., Xu, C., Tsvetkov, Y., Howe, B., & Wang, L. L. (2025) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00754 · Cited by 70 · see citing works
Survey on Factuality in Large Language Models
Wang, C., Liu, X., Yue, Y., Guo, Q., Hu, X., Tang, X., Zhang, T., Cheng, J., Yao, Y., Hu, X., et al. (2025) · ACM Computing Surveys · doi:10.1145/3742420 · Cited by 221 · see citing works
Self-citationKenthapadi, K., Sameki, M., & Taly, A. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671467 · Cited by 36 · see citing works
Chen, F., Li, Y., Chen, Y.-L., Bian, Z.-X., Duo, L., Zhou, Q., & Zhang, L. (2025) · Journal of Evidence-Based Medicine · doi:10.1111/jebm.70075 · Cited by 24 · see citing works
Self-citationHuang, K.-H., Chan, H. P., Fung, Y. R., Qiu, H., Zhou, M., Joty, S., Chang, S., & Ji, H. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3513320 · Cited by 34 · see citing works
Self-citationMitigating hallucinations in healthcare AI: a systematic review of evidence-based strategies
Basu, S., & Huynh, B. Q. (2026) · BMC Health Services Research · doi:10.1186/s12913-026-14851-1 · Cited by 11 · see citing works
Conformity in large language models
Zhu, X., Zhang, C., Stafford, T., Collier, N., & Vlachos, A. (2025) · Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2025.acl-long.195 · Cited by 10 · see citing works
Visual hallucination detection in large vision-language models via evidential conflict
Huang, T., Liu, Z., Wang, R., Zhang, Y., & Jing, L. (2025) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2025.109507 · Cited by 6 · see citing works
Leveraging Multimodal Retrieval-Augmented Generation for Cyber Attack Detection in Transit Systems
Munir, M. B., Cai, Y., Khan, L. R., & Thuraisingham, B. M. (2024) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa62245.2024.00046 · Cited by 3 · see citing works
Do Large Language Models Know When They Lack Knowledge?
Qin, S., Zhou, L., Sun, L., & wang, N. (2026) · Electronics · doi:10.3390/electronics15020253 · Cited by 2 · see citing works
Identifying and Mitigating API Misuse in Large Language Models
Zhuo, T. Y., He, J., Sun, J., Xing, Z., Lo, D., Grundy, J., & Du, X. (2026) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2026.3651566 · Cited by 5 · see citing works
Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval
Ji, L., Guo, F., Chen, T., Gu, Q., Wang, X., Xi, N., Wang, Y., Yu, P., Zhao, Y., Lei, H., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-88714-7_27 · Cited by 1 · see citing works
Self-citationAbumelha, M., ALGhamdi, A. S. A.-M., Fayoumi, A. G., & Ragab, M. (2025) · JMIR Medical Informatics · doi:10.2196/78432 · Cited by 1 · see citing works
Delineating Knowledge Boundaries for Honest Large Vision-Language Models
Song, J., Hu, Y., Chen, Y., Li, H., Li, Q., Cui, L., & Du, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37174-4_3 · Cited by 1 · see citing works
Self-citationFuzzy Contrastive Decoding to Alleviate Object Hallucination in Large Vision-Language Models
Kim, J., Kim, J., Kim, Y., & 조성배 (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01913 · Cited by 1 · see citing works
Unveiling Knowledge Boundary of Large Language Models for Trustworthy Information Access
Deng, Y., Li, M., Pang, L., Zhang, W., & Lam, W. P. (2025) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3726302.3731684 · Cited by 1 · see citing works
MergeBot: A platform of semi-structured merge conflict resolution for C/C++ code
He, H., Liu, X., Xu, L., Mei, G., & Xuan, J. (2025) · SoftwareX · doi:10.1016/j.softx.2025.102144
CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From Mistakes
Zhao, H., Han, J., Shi, J., Du, C., Liang, J., Xiao, Y., Zhou, W., Sun, Z., & Yu, F. (2025) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3746252.3761096
When Forgetting Reveals: Black-Box Inversion Attacks on Unlearning in Large Language Models
Zhang, Z., Wu, B., & Yuan, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-16092-8_38
Retrieval Augmented Generation Framework for the Nepali Legal Domain Question Answering
Wagle, S., Adhikari, A., Khanal, R., Bhandari, B., Manandhar, P., Acharya, P., & Bal, B. K. (2026) · doi:10.1109/icnlp69856.2026.11528061
How Digital Literacy Affects AI Literacy Among Preservice Teachers: Media Literacy as a Moderator
YİĞİT, M. F. (2026) · Participatory Educational Research · doi:10.17275/per.26.59.13.4
Navigating Examination Regulations: Reliable Chatbot Support for Students
Reid, S. A., Kammer, F., Lang, N., Ritz, H., Siepermann, M., & Wölfer, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-30784-2_30
Siddiqui, S. M. T., Ononto, A. J., Singhal, A., & Khan, L. R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-33260-8_14
Towards AI-assisted metadata generation for improved description of geospatial data
Leo, M. D., Tiouassiouine-Maes, I., Escriu, J., Lowenthal, H., Bacco, M., & Minghini, M. (2026) · Open Research Europe · doi:10.12688/openreseurope.24273.1
Retrieval-Augmented Generation (RAG)— From Modular to Agentic Systems
Dong, X. L., Sharma, S., Sun, K., Wang, J., Xia, Y., Yang, X. M., Yih, S., & Zhang, F. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3816460
Causal evidence that language models use confidence to drive behaviour
Kumaran, D., Daw, N. D., Osindero, S., Veličković, P., & Pătrăucean, V. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01293-x · Cited by 1 · see citing works
CARE-KGQA: Refusal-Aware Answerability Recovery for Knowledge Graph Question Answering
Kong, K., & Zhou, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5696-9_20
Shen, X., Shu, Z., Bao, Z., & Zhang, Y. (2026) · Technologies · doi:10.3390/technologies14100662
Li, J., Niu, J., Ding, Y., & Yi, P. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729385
- Authors
- Zhang, H., Diao, S., Lin, Y., Fung, Y., Lian, Q., Wang, X., Chen, Y., Ji, H., & Zhang, T.
- Affiliations
- University of Illinois Urbana-Champaign (US)
- Venue
- Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 7113-7139
- OpenAlex
- W4401042338
- Cited by
- 28
- References
- 0
- Citations by year
- 2026: 15 · 2025: 10 · 2024: 3
- FWCI
- 8.08
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion, cc-by)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Funders
- Defense Advanced Research Projects Agency (FA8650-23-C-7316)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- large language models, self-knowledge
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
