---
title: "Towards Knowledge Checking in Retrieval-augmented"
description: "The work matters because it offers a cheap, model-internal filter that strengthens RAG against noisy… 32 references, cited by 9 papers here."
authors: ["Shenglai Zeng", "Jiankun Zhang", "Bingheng Li", "Yuping Lin", "Tianqi Zheng", "Dante Everaert", "Hanqing Lu", "Hui Liu", "Hui Liu", "Yue Xing", "Monica Xiao Cheng", "Jiliang Tang"]
year: 2025
venue: "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.naacl-long.151/"
doi: "10.18653/v1/2025.naacl-long.151"
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/zeng-2025-knowledge-checking-retrieval-augmented-generation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zeng-2025-knowledge-checking-retrieval-augmented-generation/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/) / Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective

# Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective

**Authors:** [Shenglai Zeng](https://md.research.elamur.ai/free/en/authors/shenglai-zeng/), [Jiankun Zhang](https://md.research.elamur.ai/free/en/authors/jiankun-zhang/), Bingheng Li, [Yuping Lin](https://md.research.elamur.ai/free/en/authors/yuping-lin/), [Tianqi Zheng](https://md.research.elamur.ai/free/en/authors/tianqi-zheng/), Dante Everaert, [Hanqing Lu](https://md.research.elamur.ai/free/en/authors/hanqing-lu/), [Hui Liu](https://md.research.elamur.ai/free/en/authors/hui-liu/), [Hui Liu](https://md.research.elamur.ai/free/en/authors/hui-liu/), [Yue Xing](https://md.research.elamur.ai/free/en/authors/yue-xing/), [Monica Xiao Cheng](https://md.research.elamur.ai/free/en/authors/monica-xiao-cheng/) and [Jiliang Tang](https://md.research.elamur.ai/free/en/authors/jiliang-tang/) · **Year:** 2025 · **Venue:** [Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2025](https://md.research.elamur.ai/free/en/venues/naacl/2025/)) · **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/2025.naacl-long.151/) · [PDF](https://aclanthology.org/2025.naacl-long.151.pdf) · [DOI 10.18653/v1/2025.naacl-long.151](https://doi.org/10.18653/v1/2025.naacl-long.151) · [OpenAlex](https://openalex.org/W4411119855)

**Citations:** 5 citations (OpenAlex, 2026-10-14) · [9](https://md.research.elamur.ai/free/en/papers/zeng-2025-knowledge-checking-retrieval-augmented-generation/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
RAG systems often fail when the retrieved passages are misleading (for example, after PoisonedRAG-style injection of false answers) or only loosely related to the question. LLMs tend to trust such context over what they already know. The authors frame knowledge checking as four tasks:
- **Internal Knowledge Checking**: does the model already know the answer?
- **Informed Helpfulness Checking**: is the context useful when the model has that knowledge?
- **Uninformed Helpfulness Checking**: is the context useful when the model lacks it?
- **Contradiction Checking**: does the context conflict with the model's own knowledge?

Baselines included prompting (direct, ICL, CoT, Self-RAG), token probabilities and perplexity, and none handled these tasks well. The authors instead probe the model's hidden states, building classifiers on Mistral-7B-Instruct-v0.1 representations. Positive and negative samples separate clearly in representation space, so these classifiers clearly beat the baselines. Using them to discard contradictory and unhelpful passages before generation noticeably improves RAG answers, even with a poisoned knowledge base. The work matters because it offers a cheap, model-internal filter that strengthens RAG against noisy retrieval.

## Key points
- Two representation-based checkers are proposed, both using the last input token's final-layer representation:
  - **Rep-PCA**: difference vectors of sample pairs are projected onto the top two PCA components, then classified with logistic regression.
  - **Rep-Con**: an MLP is trained with a margin-based contrastive loss.
- On internal knowledge checking, Rep-Con reaches an accuracy of 0.78 and Rep-PCA 0.75. Prompting baselines score roughly 0.47–0.54 and probability/perplexity signals roughly 0.55–0.69.
- On NQ, filtering almost entirely removes injected misleading passages for noisy queries and reduces unhelpful ones. For clean queries it also raises the share of helpful contexts. PopQA results are reported in an appendix.
- The authors acknowledge a limitation: when the LLM itself lacks knowledge, it cannot reliably judge whether the context is correct. External sources are likely needed in that case.
- Code is available at github.com/slz-ai/RAG_Knowledge_Checking.

*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

- [Amazon](https://md.research.elamur.ai/free/en/companies/amazon/) — Company, Seattle, United States · 112 works · 40,565 citations
- [Michigan State University](https://md.research.elamur.ai/free/en/universities/michigan-state-university/) — University, East Lansing, United States · 23 works · 1,077 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works

## Cite

Cite as: Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Hui Liu, Yue Xing, Monica Xiao Cheng and Jiliang Tang. 2025. Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).

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

```bibtex
@inproceedings{zeng2025knowledge,
  title = {{Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective}},
  author = {Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Hui Liu, Yue Xing, Monica Xiao Cheng and Jiliang Tang},
  booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.naacl-long.151},
  url = {https://doi.org/10.18653/v1/2025.naacl-long.151}
}
```

- [← previous Towards Inclusive Arabic LLMs: A Culturally Aligned Benchmark in Arabic Large Language Model Evaluation](https://md.research.elamur.ai/free/en/papers/nacar-2025-inclusive-arabic-llms-culturally-aligned/)
- [next → TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairs](https://md.research.elamur.ai/free/en/papers/basar-2025-turblimp-turkish-benchmark-linguistic-minimal/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/)

## References

32 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Zhengbao Jiang, Frank F Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023b. [Active retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/jiang-2023-active-retrieval-augmented-generation/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7969–7992.
2. Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems, 33:18661–18673. [find](https://scholar.google.com/scholar?q=Prannay+Khosla%2C+Piotr+Teterwak%2C+Chen+Wang%2C+Aaron+Sarna%2C+Yonglong+Tian%2C+Phillip+Isola%2C+Aaron+Maschinot%2C+Ce+Liu%2C+and+Dilip+Krishnan%2E+2020%2E+Supervised+contrastive+learning%2E+Advances+in+neural+information)
3. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, et al. 2019. [Natural questions: a benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association for Computational Linguistic…
4. Yuping Lin, Pengfei He, Han Xu, Yue Xing, Makoto Yamada, Hui Liu, and Jiliang Tang. 2024. Towards understanding jailbreak attacks in llms: A representation space analysis. arXiv preprint arXiv:2406.10794. [find](https://scholar.google.com/scholar?q=Yuping+Lin%2C+Pengfei+He%2C+Han+Xu%2C+Yue+Xing%2C+Makoto+Yamada%2C+Hui+Liu%2C+and+Jiliang+Tang%2E+2024%2E+Towards+understanding+jailbreak+attacks+in+llms%3A+A+representation+space+analysis%2E+arXiv+preprint+arXiv%3A2406%2E10)
5. Huanshuo Liu, Hao Zhang, Zhijiang Guo, Kuicai Dong, Xiangyang Li, Yi Quan Lee, Cong Zhang, and Yong Liu. 2024a. Ctrla: Adaptive retrieval-augmented generation via probe-guided control. arXiv preprint arXiv:2405.18727. — [arXiv:2405.18727](https://arxiv.org/abs/2405.18727) [find](https://scholar.google.com/scholar?q=Huanshuo+Liu%2C+Hao+Zhang%2C+Zhijiang+Guo%2C+Kuicai+Dong%2C+Xiangyang+Li%2C+Yi+Quan+Lee%2C+Cong+Zhang%2C+and+Yong+Liu%2E+2024a%2E+Ctrla%3A+Adaptive+retrieval%2Daugmented+generation+via+probe%2Dguided+control%2E+arXiv+preprint+)
6. Jerry Liu. 2022. Llamaindex. 11 2022. [https://github.com/jerryjliu/llama_index](https://github.com/jerryjliu/llama_index). [↗](https://github.com/jerryjliu/llama_index)
7. Yanming Liu, Xinyue Peng, Xuhong Zhang, Weihao Liu, Jianwei Yin, Jiannan Cao, and Tianyu Du. 2024b. Ra-isf: Learning to answer and understand from retrieval augmentation via iterative self-feedback. arXiv preprint arXiv:2403.06840. [find](https://scholar.google.com/scholar?q=Yanming+Liu%2C+Xinyue+Peng%2C+Xuhong+Zhang%2C+Weihao+Liu%2C+Jianwei+Yin%2C+Jiannan+Cao%2C+and+Tianyu+Du%2E+2024b%2E+Ra%2Disf%3A+Learning+to+answer+and+understand+from+retrieval+augmentation+via+iterative+self%2Dfeedback%2E+a)
8. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (V… [find](https://scholar.google.com/scholar?q=Alex+Mallen%2C+Akari+Asai%2C+Victor+Zhong%2C+Rajarshi+Das%2C+Daniel+Khashabi%2C+and+Hannaneh+Hajishirzi%2E+2023%2E+When+not+to+trust+language+models%3A+Investigating+effectiveness+of+parametric+and+non%2Dparametric+mem)
9. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in gpt. Advances in Neural Information Processing Systems, 35:17359–17372. [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+David+Bau%2C+Alex+Andonian%2C+and+Yonatan+Belinkov%2E+2022%2E+Locating+and+editing+factual+associations+in+gpt%2E+Advances+in+Neural+Information+Processing+Systems%2C+35%3A17359%E2%80%9317372%2E)
10. E Mozharovskii. 2024. Evaluating retrieval-augmented generation (rag) techniques in enhancing lms for coding tasks. Universum: tekhnicheskie nauki: elektron. nauchn. zhurn, (6):123. [find](https://scholar.google.com/scholar?q=E+Mozharovskii%2E+2024%2E+Evaluating+retrieval%2Daugmented+generation+%28rag%29+techniques+in+enhancing+lms+for+coding+tasks%2E+Universum%3A+tekhnicheskie+nauki%3A+elektron%2E+nauchn%2E+zhurn%2C+%286%29%3A123%2E)
11. Shiyu Ni, Keping Bi, Jiafeng Guo, and Xueqi Cheng. 2024. When do LLMs need retrieval augmentation? mitigating LLMs’ overconfidence helps retrieval augmentation. In Findings of the Association for Computational Linguistics ACL 2024, pages 11375–11388, Bangkok, Thailand and virtual meeting. Associatio… [find](https://scholar.google.com/scholar?q=Shiyu+Ni%2C+Keping+Bi%2C+Jiafeng+Guo%2C+and+Xueqi+Cheng%2E+2024%2E+When+do+LLMs+need+retrieval+augmentation%3F+mitigating+LLMs%E2%80%99+overconfidence+helps+retrieval+augmentation%2E+In+Findings+of+the+Association+for+Comp)
12. Dimitrios P Panagoulias, Maria Virvou, and George A Tsihrintzis. 2024. Augmenting large language models with rules for enhanced domain-specific interactions: The case of medical diagnosis. Electronics, 13(2):320. [find](https://scholar.google.com/scholar?q=Dimitrios+P+Panagoulias%2C+Maria+Virvou%2C+and+George+A+Tsihrintzis%2E+2024%2E+Augmenting+large+language+models+with+rules+for+enhanced+domain%2Dspecific+interactions%3A+The+case+of+medical+diagnosis%2E+Electronics)
13. Md Rizwan Parvez, Wasi Ahmad, Saikat Chakraborty, Baishakhi Ray, and Kai-Wei Chang. 2021. [Retrieval augmented code generation and summarization](https://md.research.elamur.ai/free/en/papers/parvez-2021-retrieval-augmented-code-generation-summarization/). In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2719–2734.
14. Nicholas Pipitone and Ghita Houir Alami. 2024. Legalbench-rag: A benchmark for retrieval-augmented generation in the legal domain. arXiv preprint arXiv:2408.10343. [find](https://scholar.google.com/scholar?q=Nicholas+Pipitone+and+Ghita+Houir+Alami%2E+2024%2E+Legalbench%2Drag%3A+A+benchmark+for+retrieval%2Daugmented+generation+in+the+legal+domain%2E+arXiv+preprint+arXiv%3A2408%2E10343%2E)
15. Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. 2023. [In-context retrieval-augmented language models](https://md.research.elamur.ai/free/en/papers/ram-2023-context-retrieval-augmented-language-models/). arXiv preprint arXiv:2302.00083.
16. Ruiyang Ren, Yuhao Wang, Yingqi Qu, Wayne Xin Zhao, Jing Liu, Hao Tian, Hua Wu, Ji-Rong Wen, and Haifeng Wang. 2023. [Investigating the factual knowledge boundary of large language models with retrieval augmentation](https://md.research.elamur.ai/free/en/papers/ren-2025-investigating-factual-knowledge-boundary-large/). arXiv preprint arXiv:2307.11019.
17. Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2023. [Replug: Retrieval-augmented black-box language models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/). arXiv preprint arXiv:2301.12652.
18. Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, Tharindu Kaluarachchi, Rajib Rana, and Suranga Nanayakkara. 2023. [Improving the domain adaptation of retrieval augmented generation (rag) models for open domain question answering](https://md.research.elamur.ai/free/en/papers/siriwardhana-2023-improving-domain-adaptation-retrieval-augmented/). Transactions of the Association for Computational Linguistics,…
19. Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, and Xueqi Cheng. 2024. Blinded by generated contexts: How language models merge generated and retrieved contexts for open-domain qa? arXiv preprint arXiv:2401.11911. — [arXiv:2401.11911](https://arxiv.org/abs/2401.11911) [find](https://scholar.google.com/scholar?q=Hexiang+Tan%2C+Fei+Sun%2C+Wanli+Yang%2C+Yuanzhuo+Wang%2C+Qi+Cao%2C+and+Xueqi+Cheng%2E+2024%2E+Blinded+by+generated+contexts%3A+How+language+models+merge+generated+and+retrieved+contexts+for+open%2Ddomain+qa%3F+arXiv+prep)
20. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford alpaca: An instruction-following llama model. [https://github.com/tatsu-lab/stanford_alpaca](https://github.com/tatsu-lab/stanford_alpaca). [↗](https://github.com/tatsu-lab/stanford_alpaca)
21. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288.
22. Dave Van Veen, Cara Van Uden, Louis Blankemeier, Jean-Benoit Delbrouck, Asad Aali, Christian Bluethgen, Anuj Pareek, Malgorzata Polacin, William Collins, Neera Ahuja, et al. 2023. [Clinical text summarization: Adapting large language models can outperform human experts](https://md.research.elamur.ai/free/en/papers/veen-2023-adapted-large-language-models-outperform/). arXiv preprint arXiv:2309.0743…
23. Hongru Wang, Boyang Xue, Baohang Zhou, Tianhua Zhang, Cunxiang Wang, Guanhua Chen, Huimin Wang, and Kam-fai Wong. 2024. [Self-dc: When to retrieve and when to generate?](https://md.research.elamur.ai/free/en/papers/zou-2023-representation-engineering-top-down-approach/) self divide-and-conquer for compositional unknown questions. arXiv preprint arXiv:2402.13514. et al. 2023. Representation engineerin…
24. Wei Zou, Runpeng Geng, Binghui Wang, and Jinyuan Jia. 2024. Poisonedrag: Knowledge poisoning attacks to retrieval-augmented generation of large language models. [find](https://scholar.google.com/scholar?q=Wei+Zou%2C+Runpeng+Geng%2C+Binghui+Wang%2C+and+Jinyuan+Jia%2E+2024%2E+Poisonedrag%3A+Knowledge+poisoning+attacks+to+retrieval%2Daugmented+generation+of+large+language+models%2E)
25. Yike Wang, Shangbin Feng, Heng Wang, Weijia Shi, Vidhisha Balachandran, Tianxing He, and Yulia Tsvetkov. 2023a. [Resolving knowledge conflicts in large language models](https://md.research.elamur.ai/free/en/papers/wang-2023-resolving-knowledge-conflicts-large-language/). arXiv preprint arXiv:2310.00935.
26. Yile Wang, Peng Li, Maosong Sun, and Yang Liu. 2023b. [Self-knowledge guided retrieval augmentation for large language models](https://md.research.elamur.ai/free/en/papers/wang-2023-self-knowledge-guided-retrieval-augmentation/). In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10303–10315.
27. Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou, and Yu Su. [Adaptive chameleon or stubborn sloth: Revealing the behavior of large language models in knowledge conflicts](https://md.research.elamur.ai/free/en/papers/xie-2023-adaptive-chameleon-stubborn-sloth-revealing/). In The Twelfth International Conference on Learning Representations. Ori Yoran, Tomer Wolfson, Ori Ram, and Jonathan Berant. Making…
28. Shenglai Zeng, Jiankun Zhang, Pengfei He, Yue Xing, Yiding Liu, Han Xu, Jie Ren, Shuaiqiang Wang, Dawei Yin, Yi Chang, et al. 2024. The good and the bad: Exploring privacy issues in retrieval-augmented generation (rag). ACL Findings. [find](https://scholar.google.com/scholar?q=Shenglai+Zeng%2C+Jiankun+Zhang%2C+Pengfei+He%2C+Yue+Xing%2C+Yiding+Liu%2C+Han+Xu%2C+Jie+Ren%2C+Shuaiqiang+Wang%2C+Dawei+Yin%2C+Yi+Chang%2C+et+al%2E+2024%2E+The+good+and+the+bad%3A+Exploring+privacy+issues+in+retrieval%2Daugmente)
29. Zihan Zhang, Meng Fang, and Ling Chen. 2024. Retrievalqa: Assessing adaptive retrieval-augmented generation for short-form open-domain question answering. arXiv preprint arXiv:2402.16457. [find](https://scholar.google.com/scholar?q=Zihan+Zhang%2C+Meng+Fang%2C+and+Ling+Chen%2E+2024%2E+Retrievalqa%3A+Assessing+adaptive+retrieval%2Daugmented+generation+for+short%2Dform+open%2Ddomain+question+answering%2E+arXiv+preprint+arXiv%3A2402%2E16457%2E)
30. Chujie Zheng, Fan Yin, Hao Zhou, Fandong Meng, Jie Zhou, Kai-Wei Chang, Minlie Huang, and Nanyun Peng. 2024. Prompt-driven llm safeguarding via directed representation optimization. arXiv preprint arXiv:2401.18018. [find](https://scholar.google.com/scholar?q=Chujie+Zheng%2C+Fan+Yin%2C+Hao+Zhou%2C+Fandong+Meng%2C+Jie+Zhou%2C+Kai%2DWei+Chang%2C+Minlie+Huang%2C+and+Nanyun+Peng%2E+2024%2E+Prompt%2Ddriven+llm+safeguarding+via+directed+representation+optimization%2E+arXiv+preprint+arX)
31. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2023. [Judging llm-as-a-judge with mt-bench and chatbot arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). Advances in Neural Information Processing Systems, 36:46595–46623.
32. Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, [find](https://scholar.google.com/scholar?q=Andy+Zou%2C+Long+Phan%2C+Sarah+Chen%2C+James+Campbell%2C+Phillip+Guo%2C+Richard+Ren%2C+Alexander+Pan%2C+Xuwang+Yin%2C+Mantas+Mazeika%2C+Ann%2DKathrin+Dombrowski%2C)

*Updated 1 November 2026*