The Hallucination Tax of Reinforcement Finetuning
Open accessAbstract
Reinforcement finetuning (RFT) has become a standard approach for enhancing the reasoning capabilities of large language models (LLMs).However, its impact on model trustworthiness remains underexplored.In this work, we identify and systematically study a critical side effect of RFT, which we term the hallucination tax: a degradation in refusal behavior causing models to produce hallucinated answers to unanswerable questions confidently.To investigate this, we introduce SUM (Synthetic Unanswerable Math), a high-quality dataset of unanswerable math problems designed to probe models' ability to recognize an unanswerable question by reasoning from the insufficient or ambiguous information.Our results show that standard RFT training could reduce model refusal rates by more than 80%, which significantly increases model's tendency to hallucinate.We further demonstrate that incorporating just 10% SUM during RFT substantially restores appropriate refusal behavior, with minimal accuracy trade-offs on solvable tasks.Crucially, this approach enables LLMs to leverage inference-time compute to reason about their own uncertainty and knowledge boundaries, improving generalization not only to outof-domain math problems but also to factual question answering tasks.
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?
Reinforcement fine-tuning can make LLMs less likely to refuse unanswerable questions.
“Song et al. (2025) warn that reinforcement fine-tuning can make LLMs less likely to refuse unanswerable questions.”
From HalluHard: A Hard Multi-Turn Hallucination Benchmark (2026) · cites this paper as Song et al. (2025)
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
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · see citing works
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
Guo, D., Yang, D., Zhang, H., Song, J., Wang, P., Zhu, Q., Xu, R., Zhang, R., Ma, S., Bi, X., et al. (2025) · Nature · doi:10.1038/s41586-025-09422-z · Cited by 1,701 · see citing works
Aligning Large Multimodal Models with Factually Augmented RLHFPreprint
Sun, Z., Shen, S., Cao, S.-C., Liu, H., Li, C., Shen, Y., Gan, C., Gui, L., Wang, Y.-X., Yang, Y., et al. (2023) · Annual Meeting of the Association for Computational Linguistics · doi:10.48550/arxiv.2309.14525 · Cited by 914 · see citing works
TruthfulQA: Measuring How Models Mimic Human Falsehoods
Lin, S., Hilton, J., & Evans, O. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.229 · Cited by 904 · see citing works
Training Verifiers to Solve Math Word Problems
Cobbe, K., Kosaraju, V., Bavarian, M., Chen, M., Jun, H., Kaiser, L., Plappert, M., Tworek, J., Hilton, J., Nakano, R., et al. (2021) · arXiv · doi:10.48550/arxiv.2110.14168 · Cited by 575 · see citing works
Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Vaughan, A., et al. (2024) · arXiv · doi:10.48550/arxiv.2407.21783 · Cited by 505 · see citing works
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Yu, Q., Zhang, Z., Zhu, R., Yuan, Y., Zuo, X., Yue, Y., Dai, W., Fan, T., Liu, G., liu, J., et al. (2025) · neural information processing systems · doi:10.52202/085713-3775 · Cited by 393 · see citing works
An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination EvaluationPreprint
Wang, J.-Y., Wang, Y.-H., Xu, G., Zhang, J., Gu, Y., Jia, H.-T., Xu, H., Yan, M., Zhang, J., & Sang, J.-T. (2023) · arXiv.org · doi:10.48550/arxiv.2311.07397 · Cited by 356 · see citing works
He, C., Luo, R., Bai, Y., Hu, S., Thai, Z. L., Shen, J., Hu, J., Han, X., Huang, Y., Zhang, Y., et al. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.211 · Cited by 146 · see citing works
A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
Tonmoy, S. M. T. I., Zaman, S. M. M., Jain, V., Rani, A., Rawte, V., Chadha, A., & Das, A. (2024) · arXiv · doi:10.48550/arxiv.2401.01313 · Cited by 129 · see citing works
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Shao, Z., Wang, P., Zhu, Q., Xu, R., Song, J., Bi, X., Zhang, H., Zhang, M., Li, Y. K., Wu, Y., et al. (2024) · arXiv · doi:10.48550/arxiv.2402.03300 · Cited by 101 · see citing works
Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
Gekhman, Z., Yona, G., Aharoni, R., Eyal, M., Feder, A., Reichart, R., & Herzig, J. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.444 · Cited by 86 · see citing works
How Language Model Hallucinations Can Snowball
Zhang, M., Press, O., Merrill, W., Liu, A., & Smith, N. A. (2023) · arXiv · doi:10.48550/arxiv.2305.13534 · Cited by 77 · see citing works
Do Large Language Models Know What They Don’t Know?
Yin, Z., Sun, Q., Guo, Q., Wu, J., Qiu, X., & Huang, X. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.551 · Cited by 75 · see citing works
HybridFlow: A Flexible and Efficient RLHF Framework
Sheng, G., Zhang, C., Ye, Z., Wu, X., Zhang, W., Zhang, R., Peng, Y., Lin, H., & Wu, C. (2025) · Proceedings of the Twentieth European Conference on Computer Systems · doi:10.1145/3689031.3696075 · Cited by 74 · see citing works
The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
Li, J., Chen, J., Ren, R., Cheng, X., Zhao, X., Nie, J.-Y., & Wen, J.-R. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.586 · Cited by 70 · see citing works
Lightman, H., Kosaraju, V., Burda, Y., Edwards, H., Baker, B., Lee, T., Leike, J., Schulman, J., Sutskever, I., & Cobbe, K. (2023) · arXiv · doi:10.48550/arxiv.2305.20050 · Cited by 65 · see citing works
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language ModelsPreprint
Gao, B., Song, F., Yang, Z., Cai, Z., Miao, Y., Dong, Q., Li, L., Ma, C., Chen, L., Xu, R., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.07985 · Cited by 50 · see citing works
Phi-4-reasoning Technical ReportPreprint
Abdin, M., Agarwal, S., Awadallah, A. H., Balachandran, V., Behl, H. S., Chen, L., de Rosa, G., Gunasekar, S., Javaheripi, M., Joshi, N., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.21318 · Cited by 42 · see citing works
LIMR: Less is More for RL ScalingPreprint
Li, X., Zou, H., & Liu, P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.11886 · Cited by 29 · see citing works
Simple synthetic data reduces sycophancy in large language models
Wei, J., Huang, D., Lu, Y., Zhou, D., & Le, Q. V. (2023) · arXiv · doi:10.48550/arxiv.2308.03958 · Cited by 28 · see citing works
Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced ReasoningPreprint
Zhang, S., Dong, Y., Zhang, J., Kautz, J., Catanzaro, B., Tao, A., Wu, Q., Yu, Z., & Liu, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.00024 · Cited by 24 · see citing works
Efficient Reinforcement Finetuning via Adaptive Curriculum LearningPreprint
Shi, T., Wu, Y., Song, L., Zhou, T., & Zhao, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.05520 · Cited by 19 · see citing works
Self-citationAbsolute Zero: Reinforced Self-play Reasoning with Zero Data
Zhao, A., Wu, Y., Yue, Y., Wu, T., Xu, Q., Yue, Y., Lin, M., Wang, S., Wu, Q., Zheng, Z., et al. (2025) · arXiv · Cited by 13 · see citing works
Let’s Ask GNN: Empowering Large Language Model for Graph In-Context Learning
Hu, Z., Li, Y., Chen, Z., Wang, J., Liu, H., Lee, K., & Ding, K. (2024) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2024.findings-emnlp.75 · Cited by 13 · see citing works
Evaluating Hallucinations in Chinese Large Language ModelsPreprint
Cheng, Q., Sun, T., Zhang, W., Wang, S., Liu, X., Zhang, M., He, J., Huang, M., Yin, Z., Chen, K., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.03368 · Cited by 9 · see citing works
Tina: Tiny Reasoning Models via LoRAPreprint
Wang, S., Asilis, J., Akgül, Ö. F., Bilgin, E., Liu, O., & Neiswanger, W. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.15777 · Cited by 9 · see citing works
How Many Validation Labels Do You Need? Exploring the Design Space of Label-Efficient Model RankingPreprint
Hu, Z.-Y., Zhang, J.-Y., Yu, Y., Zhuang, Y.-C., & Xiong, H. (2023) · arXiv.org · doi:10.48550/arxiv.2312.01619 · Cited by 9 · see citing works
Editable Concept Bottleneck ModelsPreprint
Hu, L., Ren, C., Hu, Z., Lin, H., Wang, D., Xiong, H., Zhang, J., & Wang, D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.15476 · Cited by 8 · see citing works
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Hu, J., Zhang, Y., Han, Q., Jiang, D., Zhang, X., & Shum, H. (2025) · neural information processing systems · doi:10.52202/085713-5418 · Cited by 7 · see citing works
Semi-Supervised Concept Bottleneck Models
Hu, L., Huang, T., Xie, H., Gong, X., Ren, C., Hu, Z., Yu, L., Ma, P., & Wang, D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00204 · Cited by 7 · see citing works
Towards Acyclic Preference Evaluation of Language Models via Multiple Evaluators
Hu, Z., Zhang, J., Xiong, Z., Ratner, A., Ding, K., & Krishna, R. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i26.39343 · Cited by 7 · see citing works
Mitigating Open-Vocabulary Caption HallucinationsPreprint
Ben-Kish, A., Yanuka, M., Alper, M., Giryes, R., & Averbuch‐Elor, H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.03631 · Cited by 7 · see citing works
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Wang, Y., Yang, Q. K., Zeng, Z., Ren, L., Liu, L., Peng, B., Cheng, H., He, X., Wang, K., Gao, J., et al. (2025) · neural information processing systems · doi:10.52202/085713-4093 · Cited by 5 · see citing works
Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study
Hu, Z., Lian, J., Xiao, Z., Zhang, S., Wang, T., Yuan, N. J., Xie, X., & Xiong, H. (2025) · neural information processing systems · doi:10.52202/085713-5760 · Cited by 4 · see citing works
Treble Counterfactual VLMs: A Causal Approach to HallucinationPreprint
Li, S., Qu, J., Zhou, Y., Qin, Y., Yang, T., & Zhao, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.06169 · Cited by 4 · see citing works
HalluLens: LLM Hallucination BenchmarkPreprint
Bang, Y., Ji, Z., Schelten, A., Hartshorn, A., Fowler, T., Zhang, C., Cancedda, N., & Fung, P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.17550 · Cited by 3 · see citing works
REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage NormalizationPreprint
Hu, J., Liu, J. K., Xu, H., & Shen, W. (2024) · arXiv (Cornell University) · doi:10.13140/rg.2.2.15090.62409/3 · Cited by 2 · see citing works
Explaining Length Bias in LLM-Based Preference EvaluationsPreprint
Hu, Z., Song, L., Zhang, J., Xiao, Z., Wang, T., Chen, Z., Yuan, N. J., Lian, J., Ding, K., & Xiong, H. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.01085 · Cited by 1 · see citing works
Self-citationHuang, Z., Zou, H., Li, X., Liu, Y., Zheng, Y., Chern, E., Xia, S., Qin, Y., Yuan, W., & Liu, P. (2024) · arXiv · doi:10.48550/arxiv.2411.16489 · Cited by 1 · see citing works
A Minimalist Approach to LLM Reasoning: from Rejection Sampling to ReinforcePreprint
Xiong, W., Yao, J., Xu, Y., Pang, B., Wang, L., Sahoo, D., Li, J., Jiang, N., Zhang, T., Xiong, C., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.11343
Flagged first, then by citations
Research works printed but not linked: 19
- Yejin Bang, Ziwei Ji, Alan Schelten, Anthony Hartshorn, Tara Fowler, Cheng Zhang, Nicola Can- cedda, and Pascale Fung. 2025b. Hallulens: Llm hal- lucination benchmark. Preprint, arXiv:2504.17550. · arXiv
- Forrest Bao, Miaoran Li, Rogger Luo, and Ofer Mendelevitch. 2024. HHEM-2.1-Open. · DOI
- Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shi- rong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948. · arXiv
- Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the math dataset. NeurIPS.
- Jian Hu. 2025. Reinforce++: A simple and efficient approach for aligning large language models. arXiv preprint arXiv:2501.03262. · arXiv
- Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Jingang Wang, Zhenyu Chen, Jieyu Zhao, and Hui Xiong. 2024d. Rethinking llm-based preference eval- uation. arXiv e-prints, pages arXiv-2407.
- Zhengyu Hu, Jieyu Zhang, Haonan Wang, Siwei Liu, and Shangsong Liang. 2023a. Leveraging relational graph neural network for transductive model ensem- ble. In Proceedings of the 29th ACM SIGKDD Con- ference on Knowledge Discovery and Data Mining, pages 775-787.
- Zhengyu Hu, Jieyu Zhang, Zhihan Xiong, Alexander Ratner, Hui Xiong, and Ranjay Krishna. 2024f. Lan- guage model preference evaluation with multiple weak evaluators. arXiv preprint arXiv:2410.12869. · arXiv
- Qidong Huang, Xiaoyi Dong, Pan Zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, and Nenghai Yu. 2024a. Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. In Proceedings of the IEEE/CVF Conference on Com- puter Vision and Pattern Recognition, pages 13418- 13427.
- Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski, Vinay Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, and 1 others. 2022. Solving quan- titative reasoning problems with language models. Advances in Neural Information Processing Systems, 35:3843-3857.
- Junyi Li, Jie Chen, Ruiyang Ren, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen. 2024b. The dawn after the dark: An empirical study on factuality hallucination in large language models. arXiv preprint arXiv:2401.03205. · arXiv
- Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Hannaneh Hajishirzi, and Daniel Khashabi. 2022. When not to trust language models: Investigating effectiveness and limitations of parametric and non- parametric memories. arXiv preprint.
- Ethan Perez, Sam Ringer, Kamile Lukosiute, Karina Nguyen, Edwin Chen, Scott Heiner, Craig Pettit, Catherine Olsson, Sandipan Kundu, Saurav Kada- vath, and 1 others. 2023. Discovering language model behaviors with model-written evaluations. In Findings of the Association for Computational Lin- guistics: ACL 2023, pages 13387-13434.
- Karan Singhal, Tao Tu, Juraj Gottweis, Rory Sayres, Ellery Wulczyn, Mohamed Amin, Le Hou, Kevin Clark, Stephen R Pfohl, Heather Cole-Lewis, and 1 others. 2025. Toward expert-level medical ques- tion answering with large language models. Nature Medicine, pages 1-8.
- Yuhong Sun, Zhangyue Yin, Qipeng Guo, Jiawen Wu, Xipeng Qiu, and Hui Zhao. 2024. Benchmarking hal- lucination in large language models based on unan- swerable math word problem. In LREC/COLING.
- Tianfu Wang, Yi Zhan, Jianxun Lian, Zhengyu Hu, Nicholas Jing Yuan, Qi Zhang, Xing Xie, and Hui Xiong. 2025b. Llm-powered multi-agent framework for goal-oriented learning in intelligent tutoring sys- tem. In Companion Proceedings of the ACM on Web Conference 2025, pages 510-519.
- Yuqing Yang, Ethan Chern, Xipeng Qiu, Graham Neu- big, and Pengfei Liu. 2024. Alignment for honesty. Advances in Neural Information Processing Systems, 37:63565-63598.
- Tianyu Yu, Yuan Yao, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, and 1 others. 2024. Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback. In Proceedings of the IEEE/CVF Conference on Com- puter Vision and Pattern Recognition, pages 13807- 13816.
- Jieyu Zhang, Bohan Wang, Zhengyu Hu, Pang Wei W Koh, and Alexander J Ratner. 2024. On the trade- off of intra-/inter-class diversity for supervised pre- training. Advances in Neural Information Processing Systems, 36.
Cited by
Sorted by citations
Dasaklis, T. K., Giannopoulos, P. G., Koutras, D., Malamas, V., & Chountalas, P. T. (2026) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2026.124800 · Cited by 10 · see citing works
Thinking Out Loud: Do Reasoning Models Know When They’re Right?
Zeng, Q., Xuan, W., Cui, L., & Voigt, R. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.73 · Cited by 6 · see citing works
Explaining Length Bias in LLM-Based Preference Evaluations
Hu, Z., Song, L., Zhang, J., Xiao, Z., Wang, T., Chen, Z., Yuan, N. J., Lian, J., Ding, K., & Xiong, H. (2025) · Findings of the Association for Computational Linguistics: EMNLP 2025 · doi:10.18653/v1/2025.findings-emnlp.358 · Cited by 4 · see citing works
Self-citationAbstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
Zhai, H., Liang, J., & Kang, D. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.985 · Cited by 1 · see citing works
Toward Weight-level Self-improving Agents with Meta-knowledge DiscoveryPreprint
Zhang, T. (2025) · doi:10.36227/techrxiv.175744083.37752625/v1 · Cited by 1 · see citing works
HalluHard: A Hard Multi-Turn Hallucination Benchmark
Fan, D., Delsad, S., Flammarion, N., & Andriushchenko, M. (2026) · arXiv · doi:10.48550/arxiv.2602.01031
Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration
Wang, A., Lin, Y., Liu, J., Wu, S., Liu, H., Xiao, X., & Su, J. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i39.40621
Xu, T. R. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i48.42331
Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
Gourabathina, A., Padhi, I., Nagireddy, M., Chaudhury, S., & Sattigeri, P. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.608
PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning
Liu, L., LV, K., Chen, H., Zhang, W., Wang, Y., Liu, S., Tong, X. T., Yuan, Y., Wang, Y., Su, W., et al. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.910
Reinforcement Learning in the Era of Large Language Models: Challenges and Opportunities
Hao, Q., Chen, L., Qi, X.-K., Yuan, Y., Zong, Z., Chen, H. S., Zhao, K., Wang, S., Zhang, Y., Yuan, J., et al. (2026) · ACM Computing Surveys · doi:10.1145/3837057
To Answer or Not to Answer? Reliability-Oriented Reinforcement Learning for Visual Language Models
Jian, P., Wu, J., Wei, L., Chen, D., Guo, G., Guo, Q., & Li, J. (2026) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/2026.emnlp-main.2342
- Authors
- Song, L., Shi, T., & Zhao, J.
- Affiliations
- University of Southern California (US)
- Venue
- Findings of the Association for Computational Linguistics: EMNLP 2025
- Published
- 2025
- Pages
- 2105-2120
- OpenAlex
- W4416035861
- Cited by
- 10
- References
- 39
- Citations by year
- 2026: 8 · 2025: 2
- FWCI
- 7.02
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- 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 › Adversarial Robustness in Machine Learning
- Keywords
- large language models, refusal behavior, unanswerable questions, model credibility, uncertainty reasoning, factual question answering, out-of-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
