Elamur Research⌕
☰
home / papers / 2026 / Calibrating Inference Time Alignment with Sequence-level Risk Accumulation

Calibrating Inference Time Alignment with Sequence-level Risk Accumulation

Paper · 2026 · Shanwen Tan, Ziyang Dong, Wei Ju et al.

Summary

LLM defenses against jailbreaks often over-refuse. They block innocuous requests, such as how to "kill" a Linux process, because single tokens look dangerous. This paper presents SEAT, an inference-time decoding framework named for its approach of accumulating risk over whole sequences to calibrate alignment at test time, which treats jailbreak robustness and over-refusal as one joint objective. SEAT runs several parallel decoding branches. A multi-branch reward model, adapted from the multifurcation design in Saffron, scores the safety of all top-p candidate tokens in one forward pass. These scores are combined with the policy model's probabilities to choose continuations. A sequence-level risk monitor then smooths per-step risk with an exponential moving average. The model refuses only when the accumulated risk passes a threshold across active branches, so brief token-level spikes do not end benign answers. The authors tested SEAT on four jailbreak benchmarks and two neutral "seemingly harmful" datasets against eight baselines. They report stronger attack resistance and fewer false refusals, at a modest runtime cost. This makes SEAT a practical option for deployments where harmful and harmless queries are mixed.

Key points

  • Evaluation setup: SEAT is tested against attacks such as GCG and DeepInception, with over-refusal measured on XSTest and OR-Bench. The metrics are ASR, FPR, and an overall score called BSS.
  • Cross-architecture results: Across Mistral-7B, DeepSeek-7B, Vicuna-13B, and Llama2-13B, ASR stays between 2% and 6%. FPR ranges from 2% to 8% on XSTest and from 6% to 15% on OR-Bench.
  • Runtime (default J=4, 200 prompts per split): SEAT takes 31.4 s versus 22.8 s for greedy decoding on benign Just-Eval prompts. On the mixed 7:2:1 workload, it takes 29.2 s versus 23.3 s.
  • Sensitivity analysis (Vicuna-7B-v1.5 policy, MRM-1B reward model): Results are robust to the top-p value and the relative-risk temperature γ_rel. A small EMA coefficient ρ or too few branches J increases false refusals.
  • Availability: The code is published at github.com/ShanwenTan/SEAT. The authors note that adaptive attackers could exploit fixed thresholds.

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

🎓Tsinghua UniversityBeijing · China333 works · 87,019 citations🎓Peking UniversityBeijing · China244 works · 39,359 citations🎓Nanyang Technological UniversitySingapore · Singapore156 works · 25,644 citations🎓Sichuan UniversityChengdu · China14 works · 1,293 citations🎓University of International Business and EconomicsBeijing · China7 works · 37 citations🎓Great Bay UniversityDongguan · China3 works · 3 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Bias, fairness & safety · 517 works

Cite

Cite as Shanwen Tan, Ziyang Dong, Wei Ju, Yiwei Fu, Hao Wu, Kun Wang, Yifan Wang and Ziyue Qiao. 2026. Calibrating Inference Time Alignment with Sequence-level Risk Accumulation. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.305

@inproceedings{tan2026calibrating,
  title = {{Calibrating Inference Time Alignment with Sequence-level Risk Accumulation}},
  author = {Shanwen Tan, Ziyang Dong, Wei Ju, Yiwei Fu, Hao Wu, Kun Wang, Yifan Wang and Ziyue Qiao},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.305},
  url = {https://doi.org/10.18653/v1/2026.acl-long.305}
}

References

69 references, 32 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Gabriel Alon and Michael Kamfonas. 2023. Detecting language model attacks with perplexity. arXiv preprint arXiv:2308.14132.
  2. Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, and 1 others. 2024. Foundational challenges in assuring alignment and safety of large language models. arXiv preprint arXiv:2404.09932. find
  3. Zouying Cao, Yifei Yang, and Hai Zhao. 2025. Scans: Mitigating the exaggerated safety for llms via safety-conscious activation steering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 23523–23531. find
  4. Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J Pappas, and Eric Wong. 2025. Jailbreaking black box large language models in twenty queries. In 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), pages 23–42. IEEE.
  5. Yangyi Chen, Hongcheng Gao, Ganqu Cui, Fanchao Qi, Longtao Huang, Zhiyuan Liu, and Maosong Sun. 2022. Why should adversarial perturbations be imperceptible? rethink the research paradigm in adversarial nlp. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pa… find
  6. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. find
  7. Justin Cui, Wei-Lin Chiang, Ion Stoica, and Cho-Jui Hsieh. 2024. Or-bench: An over-refusal benchmark for large language models. arXiv preprint arXiv:2405.20947.
  8. Shih-Chieh Dai, Jun Xu, and Guanhong Tao. 2025a. A comprehensive study of llm secure code generation. arXiv preprint arXiv:2503.15554. — [arXiv:2503.15554](https://arxiv.org/abs/2503.15554) find
  9. Sunhao Dai, Chen Xu, Shicheng Xu, Liang Pang, Zhenhua Dong, and Jun Xu. 2025b. Unifying bias and unfairness in information retrieval: New challenges in the llm era. In Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, pages 998–1001. find
  10. Badhan Chandra Das, M Hadi Amini, and Yanzhao Wu. 2025. Security and privacy challenges of large language models: A survey. ACM Computing Surveys, 57(6):1–39.
  11. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, and 181 others. 2025. Deepseek-v3 technical report. Preprint, arXiv:2… find
  12. Peng Ding, Jun Kuang, Dan Ma, Xuezhi Cao, Yunsen Xian, Jiajun Chen, and Shujian Huang. 2024. A wolf in sheep’s clothing: Generalized nested jailbreak prompts can fool large language models easily. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computationa… find
  13. Yifu Ding, Wentao Jiang, Shunyu Liu, Yongcheng Jing, Jinyang Guo, Yingjie Wang, Jing Zhang, Zengmao Wang, Ziwei Liu, and Bo Du. 2025. Dynamic parallel tree search for efficient llm reasoning. arXiv preprint arXiv:2502.16235.
  14. Lin Gui, Cristina Gârbacea, and Victor Veitch. 2024. Bonbon alignment for large language models and the sweetness of best-of-n sampling. Advances in Neural Information Processing Systems, 37:2851–2885. find
  15. Keegan Hines, Gary Lopez, Matthew Hall, Federico Zarfati, Yonatan Zunger, and Emre Kiciman. 2024. Defending against indirect prompt injection attacks with spotlighting. arXiv preprint arXiv:2403.14720. — [arXiv:2403.14720](https://arxiv.org/abs/2403.14720) find
  16. Xiaomeng Hu, Pin-Yu Chen, and Tsung-Yi Ho. 2024. Gradient cuff: Detecting jailbreak attacks on large language models by exploring refusal loss landscapes. Advances in Neural Information Processing Systems, 37:126265–126296. find
  17. James Y Huang, Sailik Sengupta, Daniele Bonadiman, Yi-an Lai, Arshit Gupta, Nikolaos Pappas, Saab Mansour, Katrin Kirchhoff, and Dan Roth. 2025. Deal: Decoding-time alignment for large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume…
  18. Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, and Tom Goldstein. 2023. Baseline defenses for adversarial attacks against aligned language models. arXiv preprint arXiv:2309.00614.
  19. Feiran Jia, Tong Wu, Xin Qin, and Anna Squicciarini. 2025. The task shield: Enforcing task alignment to defend against indirect prompt injection in llm agents. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 29680–29697.
  20. Aounon Kumar, Chirag Agarwal, Suraj Srinivas, Aaron Jiaxun Li, Soheil Feizi, and Himabindu Lakkaraju. 2023. Certifying llm safety against adversarial prompting. arXiv preprint arXiv:2309.02705.
  21. Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim, Jinwoo Shin, and Jihoon Tack. 2025. Revise: Learning to refine at test-time via intrinsic self-verification. arXiv preprint arXiv:2502.14565. — [arXiv:2502.14565](https://arxiv.org/abs/2502.14565) find
  22. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, and Angela Fan. 2024. The llama 3 herd of models. arXiv eprints, pages arXiv–2407.
  23. Xuan Li, Zhanke Zhou, Jianing Zhu, Jiangchao Yao, Tongliang Liu, and Bo Han. 2023. Deepinception: Hypnotize large language model to be jailbreaker. arXiv preprint arXiv:2311.03191.
  24. Simon Geisler, Tom Wollschläger, Mohamed Hesham Ibrahim Abdalla, Johannes Gasteiger, and Stephan Günnemann. 2024. Attacking large language models with projected gradient descent. arXiv preprint arXiv:2402.09154. — [arXiv:2402.09154](https://arxiv.org/abs/2402.09154) find
  25. Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Chandu, Chandra Bhagavatula, and Yejin Choi. 2023. The unlocking spell on base llms: Rethinking alignment via in-context learning. arXiv preprint arXiv:2312.01552.
  26. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, and Alex Vaughan. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  27. Quan Liu, Zhenhong Zhou, Longzhu He, Yi Liu, Wei Zhang, and Sen Su. 2024a. Alignment-enhanced decoding: Defending via token-level adaptive refining of probability distributions. arXiv preprint arXiv:2408.07663. — [arXiv:2408.07663](https://arxiv.org/abs/2408.07663) find
  28. Xiaogeng Liu, Nan Xu, Muhao Chen, and Chaowei Xiao. 2023a. Autodan: Generating stealthy jailbreak prompts on aligned large language models. arXiv preprint arXiv:2310.04451.
  29. Yi Liu, Gelei Deng, Zhengzi Xu, Yuekang Li, Yaowen Zheng, Ying Zhang, Lida Zhao, Tianwei Zhang, Kailong Wang, and Yang Liu. 2023b. Jailbreaking chatgpt via prompt engineering: An empirical study. arXiv preprint arXiv:2305.13860.
  30. Zheng Liu, Yujia Zhou, Yutao Zhu, Jianxun Lian, Chaozhuo Li, Zhicheng Dou, Defu Lian, and Jian-Yun Nie. 2024b. Information retrieval meets large language models. In Companion Proceedings of the ACM Web Conference 2024, pages 1586–1589. find
  31. AI @ Meta Llama Team. 2024. The llama 3 family of models. https://github.com/meta-llama/ PurpleLlama/blob/main/Llama-Guard3/1B/ MODEL_CARD.md. ↗
  32. Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, and 1 others. 2025. A survey on efficient large language model training: From data-centric perspectives. In Proceedings of the 63rd Annual Meeting of the Association for Computational…
  33. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, and Yiming Yang. 2023. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, 36:46534–46594. find
  34. Utsav Maskey, Sumit Yadav, Mark Dras, and Usman Naseem. 2025. Safeconstellations: Steering llm safety to reduce over-refusals through task-specific trajectory. arXiv preprint arXiv:2508.11290. — [arXiv:2508.11290](https://arxiv.org/abs/2508.11290) find
  35. Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian. 2025. A comprehensive overview of large language models. ACM Transactions on Intelligent Systems and Technology, 16(5):1–72.
  36. 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, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, and 181 others.… — GPT-4 Technical Report
  37. Mansi Phute, Alec Helbling, Matthew Hull, ShengYun Peng, Sebastian Szyller, Cory Cornelius, and Duen Horng Chau. 2023. Llm self defense: By self examination, llms know they are being tricked. arXiv preprint arXiv:2308.07308. find
  38. Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson. 2023. Fine-tuning aligned language models compromises safety, even when users do not intend to! arXiv preprint arXiv:2310.03693.
  39. Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson. 2024. Fine-tuning aligned language models compromises safety, even when users do not intend to! In The Twelfth International Conference on Learning Representations.
  40. Libo Qin, Qiguang Chen, Xiachong Feng, Yang Wu, Yongheng Zhang, Yinghui Li, Min Li, Wanxiang Che, and Philip S Yu. 2024. Large language models meet nlp: A survey. arXiv preprint arXiv:2405.12819. — [arXiv:2405.12819](https://arxiv.org/abs/2405.12819) find
  41. Ruizhong Qiu, Gaotang Li, Tianxin Wei, Jingrui He, and Hanghang Tong. 2025. Saffron-1: Safety inference scaling. arXiv preprint arXiv:2506.06444. — [arXiv:2506.06444](https://arxiv.org/abs/2506.06444) find
  42. Alexander Robey, Eric Wong, Hamed Hassani, and George J Pappas. 2023. Smoothllm: Defending large language models against jailbreaking attacks. arXiv preprint arXiv:2310.03684.
  43. Paul Röttger, Hannah Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, and Dirk Hovy. 2024. Xstest: A test suite for identifying exaggerated safety behaviours in large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational L…
  44. Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot, Johan Ferret, Nino Vieillard, Alexandre Ramé, Bobak Shariari, Sarah Perrin, Abe Friesen, and Geoffrey Cideron. 2024. Bond: Aligning llms with best-of-n distillation. arXiv preprint arXiv:2407.14622. find
  45. Rusheb Shah, Soroush Pour, Arush Tagade, Stephen Casper, and Javier Rando. 2023. Scalable and transferable black-box jailbreaks for language models via persona modulation. arXiv preprint arXiv:2311.03348. — [arXiv:2311.03348](https://arxiv.org/abs/2311.03348) find
  46. Tianhao Shen, Renren Jin, Yufei Huang, Chuang Liu, Weilong Dong, Zishan Guo, Xinwei Wu, Yan Liu, and Deyi Xiong. 2023. Large language model alignment: A survey. arXiv preprint arXiv:2309.15025.
  47. Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuan-Jing Huang, Xun Zhao, and Dahua Lin. 2024a. Navigating the overkill in large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), page… find
  48. Jiawen Shi, Zenghui Yuan, Yinuo Liu, Yue Huang, Pan Zhou, Lichao Sun, and Neil Zhenqiang Gong. 2024b. Optimization-based prompt injection attack to llm-asa-judge. In Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, pages 660–674. find
  49. Shezheng Song, Xiaopeng Li, Shasha Li, Shan Zhao, Jie Yu, Jun Ma, Xiaoguang Mao, Weimin Zhang, and Meng Wang. 2025. How to bridge the gap between modalities: Survey on multimodal large language model. IEEE Transactions on Knowledge and Data Engineering. find
  50. Qwen Team. 2025. Qwen3 technical report. Preprint, arXiv:2505.09388.
  51. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, and Shruti Bhosale. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  52. Mengting Wan, Tara Safavi, Sujay Kumar Jauhar, Yujin Kim, Scott Counts, Jennifer Neville, Siddharth Suri, Chirag Shah, Ryen W White, and Longqi Yang. 2024. Tnt-llm: Text mining at scale with large language models. In Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data minin… find
  53. Zeming Wei, Yifei Wang, Ang Li, Yichuan Mo, and Yisen Wang. 2023. Jailbreak and guard aligned language models with only few in-context demonstrations. arXiv preprint arXiv:2310.06387.
  54. Jie JW Wu and Fatemeh H Fard. 2025. Humaneval-comm: Benchmarking the communication competence of code generation for llms and llm agents. ACM Transactions on Software Engineering and Methodology, 34(7):1–42. find
  55. Yangzhen Wu, Zhiqing Sun, Shanda Li, Sean Welleck, and Yiming Yang. 2024. Inference scaling laws: An empirical analysis of compute-optimal inference for problem-solving with language models. arXiv preprint arXiv:2408.00724.
  56. Yueqi Xie, Jingwei Yi, Jiawei Shao, Justin Curl, Lingjuan Lyu, Qifeng Chen, Xing Xie, and Fangzhao Wu. 2023. Defending chatgpt against jailbreak attack via self-reminders. Nature Machine Intelligence, 5(12):1486–1496. find
  57. Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, and Radha Poovendran. 2024. Safedecoding: Defending against jailbreak attacks via safety-aware decoding. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 55…
  58. Sibo Yi, Yule Liu, Zhen Sun, Tianshuo Cong, Xinlei He, Jiaxing Song, Ke Xu, and Qi Li. 2024. Jailbreak attacks and defenses against large language models: A survey. arXiv preprint arXiv:2407.04295.
  59. Zhihang Yuan, Yuzhang Shang, Yang Zhou, Zhen Dong, Zhe Zhou, Chenhao Xue, Bingzhe Wu, Zhikai Li, Qingyi Gu, and Yong Jae Lee. 2024. Llm inference unveiled: Survey and roofline model insights. arXiv preprint arXiv:2402.16363. find
  60. Wenjun Zeng, Yuchi Liu, Ryan Mullins, Ludovic Peran, Joe Fernandez, Hamza Harkous, Karthik Narasimhan, Drew Proud, Piyush Kumar, and Bhaktipriya Radharapu. 2024. Shieldgemma: Generative ai content moderation based on gemma. arXiv preprint arXiv:2407.21772. — [arXiv:2407.21772](https://arxiv.org/abs/2407.21772) find
  61. Xinyi Zeng, Yuying Shang, Jiawei Chen, Jingyuan Zhang, and Yu Tian. 2025. Root defense strategies: Ensuring safety of llm at the decoding level. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1974–1988. find
  62. Di Zhang, Xiaoshui Huang, Dongzhan Zhou, Yuqiang Li, and Wanli Ouyang. 2024. Accessing gpt-4 level mathematical olympiad solutions via monte carlo tree self-refine with llama-3 8b: A technical report. arXiv preprint arXiv:2406.07394. find
  63. Junbo Zhang, Ran Chen, Qianli Zhou, Xinyang Deng, and Wen Jiang. 2025. Understanding and mitigating over-refusal for large language models via safety representation. arXiv preprint arXiv:2511.19009. — [arXiv:2511.19009](https://arxiv.org/abs/2511.19009) find
  64. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, and Zican Dong. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223, 1(2).
  65. Li Zhong and Zilong Wang. 2024. Can llm replace stack overflow? a study on robustness and reliability of large language model code generation. In Proceedings of the AAAI conference on artificial intelligence, volume 38, pages 21841–21849. find
  66. Chunting Zhou, Pengfei Liu, Puxin Xu, Srinivasan Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, and 1 others. 2023. Lima: Less is more for alignment. Advances in Neural Information Processing Systems, 36:55006–55021. find
  67. Andy Zou, Zifan Wang, J. Zico Kolter, and Matt Fredrikson. 2023. Universal and transferable adversarial attacks on aligned language models. Preprint, arXiv:2307.15043.
  68. Shunge Zou, Wei Ju, Ziyue Qiao, and Xiao Luo. 2025. Court simulation with multifaceted agent judgment for LLM jailbreak evaluation. find
  69. Jiahao Yu, Xingwei Lin, Zheng Yu, and Xinyu Xing. 2023. Gptfuzzer: Red teaming large language models with auto-generated jailbreak prompts. arXiv preprint arXiv:2309.10253.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tan-2026-calibrating-inference-time-alignment-sequence/