---
title: "Cognitive Analysis Graph-Guided Multi-Turn Safety"
description: "The authors propose CogGSE, a training-free framework that guides generation with a structured \"cognitive analysis graph.\"… 43 references."
authors: ["Lanxue Zhang", "Yuqiang Xie", "Fang Fang", "Yubing Ren", "Xuebin Wang", "Yanan Cao"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1558/"
doi: "10.18653/v1/2026.findings-acl.1558"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-cognitive-analysis-graph-guided-multi/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-cognitive-analysis-graph-guided-multi/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/27/) / Cognitive Analysis Graph-Guided Multi-Turn Safety Enhancement for Large Language Models

# Cognitive Analysis Graph-Guided Multi-Turn Safety Enhancement for Large Language Models

**Authors:** Lanxue Zhang, Yuqiang Xie, [Fang Fang](https://md.research.elamur.ai/free/en/authors/fang-fang/), [Yubing Ren](https://md.research.elamur.ai/free/en/authors/yubing-ren/), Xuebin Wang and [Yanan Cao](https://md.research.elamur.ai/free/en/authors/yanan-cao/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1558/) · [PDF](https://aclanthology.org/2026.findings-acl.1558.pdf) · [DOI 10.18653/v1/2026.findings-acl.1558](https://doi.org/10.18653/v1/2026.findings-acl.1558) · [OpenAlex](https://openalex.org/W7166814922)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Inference-time safety methods for LLMs often fail in multi-turn chats. They judge a question or answer on its own, apply the same defense instructions to every prompt, and ignore earlier turns. As a result, a request that looks harmless alone can become dangerous in context. The authors propose CogGSE, a training-free framework that guides generation with a structured "cognitive analysis graph." Its design draws on Cognitive Task Analysis and the Dual-Process Model of Moral Judgment. A strong LLM first produces a pool of candidate nodes of four kinds: semantic intent, sub-tasks, causal consequences with the emotions they evoke, and ethical checks. For each query, a tailored graph is retrieved from this pool and serves as a thinking draft. In later turns, graphs from earlier turns are retrieved by embedding similarity and pruned to their safety-relevant nodes. These are then merged with the current graph. Across several LLMs, safety improves by roughly 30% on average, including under jailbreak and multi-turn attacks, with no extra decoding cost. The approach makes safety reasoning more transparent and controllable without fine-tuning.

## Key points
- The graph has four node types, linked by directed edges and built step by step from a semantic root node: semantic parsing (S), task decomposition (D), causal inference (C, including emotion estimation) and ethical check (E).
- The main variant is CogGSE RAG, chosen as a balance of effectiveness and efficiency. Code is released at github.com/Qlanxue/CogGSE.
- Evaluation covers settings such as Strong Reject, Wild Jailbreak, Actor Attack (multi-turn) and MoralBench. The reported average safety gain is about 30% across LLMs.
- Ablations show that semantic-intent nodes matter in every scenario and ethical nodes matter most against jailbreaks. Dropping emotion estimation causes only a small loss, while removing the history graph G_h hurts multi-turn safety the most.
- On Qwen3-8B, CogGSE has the lowest latency, with a relative cost factor of x0.55 versus x0.60 for the NoThink setting. Limitations include dependence on retrieval and on the quality of the underlying LLM, and possible error propagation in precise-reasoning tasks such as math.

*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

- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations
- [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 188 works · 8,743 citations
- [Institute of Information Engineering](https://md.research.elamur.ai/free/en/labs/institute-of-information-engineering/) — Research institute, Beijing, China · 41 works · 1,485 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🤝 Safety Research](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · 626 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🛡️ Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · 587 works

## Cite

Cite as: Lanxue Zhang, Yuqiang Xie, Fang Fang, Yubing Ren, Xuebin Wang and Yanan Cao. 2026. Cognitive Analysis Graph-Guided Multi-Turn Safety Enhancement for Large Language Models. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhang2026cognitive,
  title = {{Cognitive Analysis Graph-Guided Multi-Turn Safety Enhancement for Large Language Models}},
  author = {Lanxue Zhang, Yuqiang Xie, Fang Fang, Yubing Ren, Xuebin Wang and Yanan Cao},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1558},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1558}
}
```

- [← previous CogNet-KG: Empowering Tutoring Dialogues with a Cognitively-Structured Knowledge Graph for STEM Learning](https://md.research.elamur.ai/free/en/papers/yu-2026-cognet-kg-empowering-tutoring-dialogues/)
- [next → Cognitive Effects and Biases in Large Language Models](https://md.research.elamur.ai/free/en/papers/schedl-2026-cognitive-effects-biases-large-language/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/27/)

## References

43 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic. 2025. Introducing claude sonnet 4.5. [https://www.anthropic.com/news/](https://www.anthropic.com/news/) claude-sonnet-4-5. Online article. [↗](https://www.anthropic.com/news/)
2. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El-Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, Scott Johnston, Sh… [find](https://scholar.google.com/scholar?q=Yuntao+Bai%2C+Andy+Jones%2C+Kamal+Ndousse%2C+Amanda+Askell%2C+Anna+Chen%2C+Nova+DasSarma%2C+Dawn+Drain%2C+Stanislav+Fort%2C+Deep+Ganguli%2C+Tom+Henighan%2C+Nicholas+Joseph%2C+Saurav+Kadavath%2C+Jackson+Kernion%2C+Tom+Conerly%2C+)
3. Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared… — [Constitutional AI: Harmlessness from AI Feedback](https://md.research.elamur.ai/free/en/papers/bai-2022-constitutional-ai-harmlessness-ai-feedback/)
4. Somnath Banerjee, Sayan Layek, Soham Tripathy, Shanu Kumar, Animesh Mukherjee, and Rima Hazra. 2025. Safeinfer: context adaptive decoding time safety alignment for large language models. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on In… [find](https://scholar.google.com/scholar?q=Somnath+Banerjee%2C+Sayan+Layek%2C+Soham+Tripathy%2C+Shanu+Kumar%2C+Animesh+Mukherjee%2C+and+Rima+Hazra%2E+2025%2E+Safeinfer%3A+context+adaptive+decoding+time+safety+alignment+for+large+language+models%2E+In+Proceeding)
5. Richard E Clark, David F Feldon, Jeroen JG Van Merrienboer, Kenneth A Yates, and Sean Early. 2008. Cognitive task analysis. In Handbook of research on educational communications and technology, pages 577–593. Routledge. [find](https://scholar.google.com/scholar?q=Richard+E+Clark%2C+David+F+Feldon%2C+Jeroen+JG+Van+Merrienboer%2C+Kenneth+A+Yates%2C+and+Sean+Early%2E+2008%2E+Cognitive+task+analysis%2E+In+Handbook+of+research+on+educational+communications+and+technology%2C+pages+)
6. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168.
7. Josef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang, and Yaodong Yang. 2024. [Safe RLHF: Safe reinforcement learning from human feedback](https://md.research.elamur.ai/free/en/papers/dai-2023-safe-rlhf-safe-reinforcement-learning/). In The Twelfth International Conference on Learning Representations.
8. DeepSeek-AI. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/).
9. Zhichen Dong, Zhanhui Zhou, Chao Yang, Jing Shao, and Yu Qiao. 2024. Attacks, defenses and evaluations for LLM conversation safety: A survey. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: L… [find](https://scholar.google.com/scholar?q=Zhichen+Dong%2C+Zhanhui+Zhou%2C+Chao+Yang%2C+Jing+Shao%2C+and+Yu+Qiao%2E+2024%2E+Attacks%2C+defenses+and+evaluations+for+LLM+conversation+safety%3A+A+survey%2E+In+Proceedings+of+the+2024+Conference+of+the+North+America)
10. Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, and Yuning Mao. 2024. [MART: Improving LLM safety with multi-round automatic red-teaming](https://md.research.elamur.ai/free/en/papers/ge-2024-mart-improving-llm-safety-multi/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human L…
11. Joshua D Greene, R Brian Sommerville, Leigh E Nystrom, John M Darley, and Jonathan D Cohen. 2001. An fmri investigation of emotional engagement in moral judgment. Science, 293(5537):2105–2108. [find](https://scholar.google.com/scholar?q=Joshua+D+Greene%2C+R+Brian+Sommerville%2C+Leigh+E+Nystrom%2C+John+M+Darley%2C+and+Jonathan+D+Cohen%2E+2001%2E+An+fmri+investigation+of+emotional+engagement+in+moral+judgment%2E+Science%2C+293%285537%29%3A2105%E2%80%932108%2E)
12. Weiyang Guo, Jing Li, Wenya Wang, Yu Li, Daojing He, Jun Yu, and Min Zhang. 2025. [MTSA: Multi-turn safety alignment for LLMs through multi-round red-teaming](https://md.research.elamur.ai/free/en/papers/guo-2025-mtsa-multi-turn-safety-alignment/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 26424–26442, Vienna,…
13. Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Michael Tontchev, Qing Hu, Brian Fuller, Davide Testuggine, and Madian Khabsa. 2023. [Llama guard: Llm-based input-output safeguard for human-ai conversations](https://md.research.elamur.ai/free/en/papers/inan-2023-llama-guard-llm-based-input/).
14. Wonje Jeung, Sangyeon Yoon, Minsuk Kahng, and Albert No. 2025. SAFEPATH: Preventing harmful reasoning in chain-of-thought via early alignment. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Wonje+Jeung%2C+Sangyeon+Yoon%2C+Minsuk+Kahng%2C+and+Albert+No%2E+2025%2E+SAFEPATH%3A+Preventing+harmful+reasoning+in+chain%2Dof%2Dthought+via+early+alignment%2E+In+The+Thirty%2Dninth+Annual+Conference+on+Neural+Informati)
15. Jianchao Ji, Yutong Chen, Mingyu Jin, Wujiang Xu, Wenyue Hua, and Yongfeng Zhang. 2025. Moralbench: Moral evaluation of llms. SIGKDD Explor. Newsl., 27(1):62–71. [find](https://scholar.google.com/scholar?q=Jianchao+Ji%2C+Yutong+Chen%2C+Mingyu+Jin%2C+Wujiang+Xu%2C+Wenyue+Hua%2C+and+Yongfeng+Zhang%2E+2025%2E+Moralbench%3A+Moral+evaluation+of+llms%2E+SIGKDD+Explor%2E+Newsl%2E%2C+27%281%29%3A62%E2%80%9371%2E)
16. Liwei Jiang, Kavel Rao, Seungju Han, Allyson Ettinger, Faeze Brahman, Sachin Kumar, Niloofar Mireshghallah, Ximing Lu, Maarten Sap, Yejin Choi, and Nouha Dziri. 2024. [Wildteaming at scale: From in-the-wild jailbreaks to (adversarially) safer language models](https://md.research.elamur.ai/free/en/papers/jiang-2024-wildteaming-scale-wild-jailbreaks-adversarially/).
17. Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, and Hongyang Zhang. 2024. RAIN: Your language models can align themselves without finetuning. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yuhui+Li%2C+Fangyun+Wei%2C+Jinjing+Zhao%2C+Chao+Zhang%2C+and+Hongyang+Zhang%2E+2024%2E+RAIN%3A+Your+language+models+can+align+themselves+without+finetuning%2E+In+The+Twelfth+International+Conference+on+Learning+Repre)
18. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. [Let’s verify step by step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/). In The Twelfth International Conference on Learning Representations.
19. Quan Liu, Zhenhong Zhou, Longzhu He, Yi Liu, Wei Zhang, and Sen Su. 2024. Alignment-enhanced decoding: Defending jailbreaks via token-level adaptive refining of probability distributions. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 2802–2816, Miam… [find](https://scholar.google.com/scholar?q=Quan+Liu%2C+Zhenhong+Zhou%2C+Longzhu+He%2C+Yi+Liu%2C+Wei+Zhang%2C+and+Sen+Su%2E+2024%2E+Alignment%2Denhanced+decoding%3A+Defending+jailbreaks+via+token%2Dlevel+adaptive+refining+of+probability+distributions%2E+In+Proceedin)
20. Yang Liu, Yuanshun Yao, Jean-François Ton, Xiaoying Zhang, Ruocheng Guo, Hao Cheng, Yegor Klochkov, Muhammad Faaiz Taufiq, and Hanguang Li. 2023. [Trustworthy llms: a survey and guideline for evaluating large language models’ alignment](https://md.research.elamur.ai/free/en/papers/liu-2023-trustworthy-llms-survey-guideline-evaluating/). ArXiv, abs/2308.05374.
21. OpenAI. 2025. Introducing gpt-5. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Introducing+gpt%2D5%2E)
22. Ethan Perez, Saffron Huang, Francis Song, Trevor Cai, Roman Ring, John Aslanides, Amelia Glaese, Nat McAleese, and Geoffrey Irving. 2022. [Red teaming language models with language models](https://md.research.elamur.ai/free/en/papers/perez-2022-red-teaming-language-models-language/). In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3419–3448, Abu…
23. Deng Qiyuan, Xuefeng Bai, Kehai Chen, Yaowei Wang, Liqiang Nie, and Min Zhang. 2025. Efficient safety alignment of large language models via preference reranking and representation-based reward modeling. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volu… [find](https://scholar.google.com/scholar?q=Deng+Qiyuan%2C+Xuefeng+Bai%2C+Kehai+Chen%2C+Yaowei+Wang%2C+Liqiang+Nie%2C+and+Min+Zhang%2E+2025%2E+Efficient+safety+alignment+of+large+language+models+via+preference+reranking+and+representation%2Dbased+reward+modeli)
24. Nils Reimers and Iryna Gurevych. 2019. [Sentence-BERT: Sentence embeddings using Siamese BERT-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992,…
25. Qibing Ren, Hao Li, Dongrui Liu, Zhanxu Xie, Xiaoya Lu, Yu Qiao, Lei Sha, Junchi Yan, Lizhuang Ma, and Jing Shao. 2025. [LLMs know their vulnerabilities: Uncover safety gaps through natural distribution shifts](https://md.research.elamur.ai/free/en/papers/ren-2025-llms-know-their-vulnerabilities-uncover/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics…
26. 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](https://md.research.elamur.ai/free/en/papers/rottger-2023-xstest-test-suite-identifying-exaggerated/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational L…
27. Feifan Song, Yuxuan Fan, Xin Zhang, Peiyi Wang, and Houfeng Wang. 2025. Instantly learning preference alignment via in-context DPO. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Lo… [find](https://scholar.google.com/scholar?q=Feifan+Song%2C+Yuxuan+Fan%2C+Xin+Zhang%2C+Peiyi+Wang%2C+and+Houfeng+Wang%2E+2025%2E+Instantly+learning+preference+alignment+via+in%2Dcontext+DPO%2E+In+Proceedings+of+the+2025+Conference+of+the+Nations+of+the+Americas)
28. Alexandra Souly, Qingyuan Lu, Dillon Bowen, Tu Trinh, Elvis Hsieh, Sana Pandey, Pieter Abbeel, Justin Svegliato, Scott Emmons, Olivia Watkins, and Sam Toyer. 2024. A strongreject for empty jailbreaks. [find](https://scholar.google.com/scholar?q=Alexandra+Souly%2C+Qingyuan+Lu%2C+Dillon+Bowen%2C+Tu+Trinh%2C+Elvis+Hsieh%2C+Sana+Pandey%2C+Pieter+Abbeel%2C+Justin+Svegliato%2C+Scott+Emmons%2C+Olivia+Watkins%2C+and+Sam+Toyer%2E+2024%2E+A+strongreject+for+empty+jailbreaks%2E)
29. Gemini Team. 2025a. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/).
30. Qwen Team. 2025b. Qwen3-max: Just scale it. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2025b%2E+Qwen3%2Dmax%3A+Just+scale+it%2E)
31. Qwen Team. 2025c. Qwen3 technical report. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2025c%2E+Qwen3+technical+report%2E)
32. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
33. Haoyu Wang, Zeyu Qin, Li Shen, Xueqian Wang, Dacheng Tao, and Minhao Cheng. 2025a. Safety reasoning with guidelines. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Haoyu+Wang%2C+Zeyu+Qin%2C+Li+Shen%2C+Xueqian+Wang%2C+Dacheng+Tao%2C+and+Minhao+Cheng%2E+2025a%2E+Safety+reasoning+with+guidelines%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Learning%2E)
34. Peiran Wang, Xiaogeng Liu, and Chaowei Xiao. 2025b. RePD: Defending jailbreak attack through a retrieval-based prompt decomposition process. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 283–294, Albuquerque, New Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Peiran+Wang%2C+Xiaogeng+Liu%2C+and+Chaowei+Xiao%2E+2025b%2E+RePD%3A+Defending+jailbreak+attack+through+a+retrieval%2Dbased+prompt+decomposition+process%2E+In+Findings+of+the+Association+for+Computational+Linguistic)
35. Zijun Wang, Haoqin Tu, Yuhan Wang, Juncheng Wu, Yanqing Liu, Jieru Mei, Brian R. Bartoldson, Bhavya Kailkhura, and Cihang Xie. 2025c. Star-1: Safer alignment of reasoning llms with 1k data. [find](https://scholar.google.com/scholar?q=Zijun+Wang%2C+Haoqin+Tu%2C+Yuhan+Wang%2C+Juncheng+Wu%2C+Yanqing+Liu%2C+Jieru+Mei%2C+Brian+R%2E+Bartoldson%2C+Bhavya+Kailkhura%2C+and+Cihang+Xie%2E+2025c%2E+Star%2D1%3A+Safer+alignment+of+reasoning+llms+with+1k+data%2E)
36. Zeming Wei, Yifei Wang, and Yisen Wang. 2023. [Jailbreak and guard aligned language models with only few in-context demonstrations](https://md.research.elamur.ai/free/en/papers/wei-2023-jailbreak-guard-aligned-language-models/). arXiv preprint arXiv:2310.06387.
37. Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff, Defu Lian, and Jian-Yun Nie. 2024. [C-pack: Packed resources for general chinese embeddings](https://md.research.elamur.ai/free/en/papers/xiao-2023-c-pack-packed-resources/). In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 641–649, New York…
38. Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, and Radha Poovendran. 2024. [SafeDecoding: Defending against jailbreak attacks via safety-aware decoding](https://md.research.elamur.ai/free/en/papers/xu-2024-safedecoding-defending-against-jailbreak-attacks/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 55…
39. Lanxue Zhang, Yanan Cao, Yuqiang Xie, Fang Fang, and Yangxi Li. 2025a. Dynamic evaluation with cognitive reasoning for multi-turn safety of large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 19588– 19608, V… [find](https://scholar.google.com/scholar?q=Lanxue+Zhang%2C+Yanan+Cao%2C+Yuqiang+Xie%2C+Fang+Fang%2C+and+Yangxi+Li%2E+2025a%2E+Dynamic+evaluation+with+cognitive+reasoning+for+multi%2Dturn+safety+of+large+language+models%2E+In+Proceedings+of+the+63rd+Annual+Mee)
40. Lanxue Zhang, Yuqiang Xie, Fang Fang, Fanglong Dong, Rui Liu, and Yanan Cao. 2025b. Metagdpo: Alleviating catastrophic forgetting with metacognitive knowledge through group direct preference optimization. [find](https://scholar.google.com/scholar?q=Lanxue+Zhang%2C+Yuqiang+Xie%2C+Fang+Fang%2C+Fanglong+Dong%2C+Rui+Liu%2C+and+Yanan+Cao%2E+2025b%2E+Metagdpo%3A+Alleviating+catastrophic+forgetting+with+metacognitive+knowledge+through+group+direct+preference+optimizat)
41. Yichi Zhang, Siyuan Zhang, Yao Huang, Zeyu Xia, Zhengwei Fang, Xiao Yang, Ranjie Duan, Dong Yan, Yinpeng Dong, and Jun Zhu. 2025c. STAIR: Improving safety alignment with introspective reasoning. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Yichi+Zhang%2C+Siyuan+Zhang%2C+Yao+Huang%2C+Zeyu+Xia%2C+Zhengwei+Fang%2C+Xiao+Yang%2C+Ranjie+Duan%2C+Dong+Yan%2C+Yinpeng+Dong%2C+and+Jun+Zhu%2E+2025c%2E+STAIR%3A+Improving+safety+alignment+with+introspective+reasoning%2E+In+Fo)
42. Zhehao Zhang, Weijie Xu, Fanyou Wu, and Chandan K. Reddy. 2025d. Falsereject: A resource for improving contextual safety and mitigating over-refusals in LLMs via structured reasoning. In Second Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Zhehao+Zhang%2C+Weijie+Xu%2C+Fanyou+Wu%2C+and+Chandan+K%2E+Reddy%2E+2025d%2E+Falsereject%3A+A+resource+for+improving+contextual+safety+and+mitigating+over%2Drefusals+in+LLMs+via+structured+reasoning%2E+In+Second+Confer)
43. Zhengyue Zhao, Xiaoyun Zhang, Kaidi Xu, Xing Hu, Rui Zhang, Zidong Du, Qi Guo, and Yunji Chen. 2024. Adversarial contrastive decoding: Boosting safety alignment of large language models via opposite prompt optimization. [find](https://scholar.google.com/scholar?q=Zhengyue+Zhao%2C+Xiaoyun+Zhang%2C+Kaidi+Xu%2C+Xing+Hu%2C+Rui+Zhang%2C+Zidong+Du%2C+Qi+Guo%2C+and+Yunji+Chen%2E+2024%2E+Adversarial+contrastive+decoding%3A+Boosting+safety+alignment+of+large+language+models+via+opposite+p)

*Updated 2 November 2026*