---
title: "PsychEthicsBench — paper by Shen et al. (2026)"
description: "Most safety evaluations of LLMs judge a model by whether it refuses harmful requests. 61 references, cited by 1 paper here."
authors: ["Yaling Shen", "Stephanie Fong", "Yiwen Jiang", "Zimu Wang", "Feilong Tang", "Qingyang Xu", "Xiangyu Zhao", "Zhongxing Xu", "Jiahe Liu", "Jinpeng Hu", "Dominic Dwyer", "Zongyuan Ge"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1971/"
doi: "10.18653/v1/2026.findings-acl.1971"
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/shen-2026-psychethicsbench-evaluating-large-language-models/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shen-2026-psychethicsbench-evaluating-large-language-models/)

[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/8/) / PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics

# PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics

**Authors:** Yaling Shen, Stephanie Fong, Yiwen Jiang, [Zimu Wang](https://md.research.elamur.ai/free/en/authors/zimu-wang/), [Feilong Tang](https://md.research.elamur.ai/free/en/authors/feilong-tang/), Qingyang Xu, [Xiangyu Zhao](https://md.research.elamur.ai/free/en/authors/xiangyu-zhao/), Zhongxing Xu, Jiahe Liu, [Jinpeng Hu](https://md.research.elamur.ai/free/en/authors/jinpeng-hu/), Dominic Dwyer and [Zongyuan Ge](https://md.research.elamur.ai/free/en/authors/zongyuan-ge/) · **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.1971/) · [PDF](https://aclanthology.org/2026.findings-acl.1971.pdf) · [DOI 10.18653/v1/2026.findings-acl.1971](https://doi.org/10.18653/v1/2026.findings-acl.1971) · [OpenAlex](https://openalex.org/W7166878727)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/shen-2026-psychethicsbench-evaluating-large-language-models/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most safety evaluations of LLMs judge a model by whether it refuses harmful requests. In mental health this is a weak measure. A curt refusal can seem cold, discourage someone from seeking help, or still contain ethically problematic content. Existing medical-ethics benchmarks also tend to assume one shared standard, usually American, and ignore differences between jurisdictions.

The authors built PsychEthicsBench, an Australian-grounded benchmark tied to 392 principles from local psychology and psychiatry guidelines. Its questions come from official exam samples plus LLM-generated items, refined through expert-in-the-loop prompting and quality control. Multiple-choice questions test ethical knowledge, and open-ended scenarios test behaviour. Responses are annotated against fine-grained violation categories, and refusal is deliberately not counted as a signal.

The authors tested 14 models. Refusal rates did not track ethical conduct. Several mental-health fine-tuned models did worse than their base backbones. Models often cited U.S. institutions despite the Australian framing, and they frequently implied professional credentials. The work shows the value of jurisdiction-aware, principle-based evaluation for mental-health AI.

## Key points
- PsychEthicsBench contains 1,377 MCQs and 2,612 open-ended questions, each mapped one-to-one to one of 392 ethical principles.
- The principles come from RANZCP (psychiatry) and the Psychology Board of Australia/AHPRA (psychology) guidelines.
- Question sources:
  - 63 verbatim National Psychology Examination (NPE) sample questions;
  - items generated with GPT-5 and Claude-Sonnet-4 through a three-stage pipeline: guideline collection, expert-in-the-loop prompt optimization, and expert-centered quality control.
- Annotation categories for violations include:
  - Credentials, Competence, Confidentiality and Misconduct;
  - Misinformation, Disrespect, Conflict and Jurisdictional issues.
- An LLM serves as judge for the annotations.
- The 14 evaluated models fall into three groups: mental-health LLMs, their base models, and medical variants, all at 14B parameters or below.
- Credential misrepresentation was widespread: SQPsychLLM-8B and Llama2-13B together produced about 1,000 such cases, which is over 38% of all open-ended questions.
- Data and code are available at github.com/ElsieSHEN/PsychEthicsBench.

*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

- [Monash University](https://md.research.elamur.ai/free/en/universities/monash-university/) — University, Melbourne, Australia · 60 works · 54,866 citations
- [University of Liverpool](https://md.research.elamur.ai/free/en/universities/university-of-liverpool/) — University, Liverpool, United Kingdom · 11 works · 546 citations
- [Hefei University of Technology](https://md.research.elamur.ai/free/en/universities/hefei-university-of-technology/) — University, Hefei, China · 10 works · 1,615 citations

📚 Shelves (8): [🖥️ 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 · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Safety Research](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · 543 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 241 works · [🩺 Health Informatics](https://md.research.elamur.ai/free/en/shelves/medicine/health-informatics/) · 184 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🛡️ Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · 517 works

## Cite

Cite as: Yaling Shen, Stephanie Fong, Yiwen Jiang, Zimu Wang, Feilong Tang, Qingyang Xu, Xiangyu Zhao, Zhongxing Xu, Jiahe Liu, Jinpeng Hu, Dominic Dwyer and Zongyuan Ge. 2026. PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics. 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{shen2026psychethicsbench,
  title = {{PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics}},
  author = {Yaling Shen, Stephanie Fong, Yiwen Jiang, Zimu Wang, Feilong Tang, Qingyang Xu, Xiangyu Zhao, Zhongxing Xu, Jiahe Liu, Jinpeng Hu, Dominic Dwyer and Zongyuan Ge},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1971},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1971}
}
```

- [← previous PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation](https://md.research.elamur.ai/free/en/papers/pulipaka-2026-psk-semeval-2026-task-9/)
- [next → Psychological Counseling Cannot Be Achieved Overnight: Automated Psychological Counseling Through Multi-Session Conversations](https://md.research.elamur.ai/free/en/papers/wang-2026-psychological-counseling-cannot-be-achieved/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/8/)

## References

61 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ahpra. 2024. Code of conduct for psychologists. [https://www.ahpra.gov.au/documents/](https://www.ahpra.gov.au/documents/) default.aspx?record=WD24%2F34313&dbid= AP&chksum=CNgh4pCJoskMdMaxBGVUkQ%3D%3D. Accessed: 2025-03-08. [↗](https://www.ahpra.gov.au/documents/)
2. Anthropic. 2025. Claude sonnet 4.5 system card. Technical report, Anthropic. Accessed: 2026-01-01. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2025%2E+Claude+sonnet+4%2E5+system+card%2E+Technical+report%2C+Anthropic%2E+Accessed%3A+2026%2D01%2D01%2E)
3. APS. 2018. Aps code of ethics. [https://psychology.org.au/getmedia/](https://psychology.org.au/getmedia/) d873e0db-7490-46de-bb57-c31bb1553025/ aps-code-of-ethics.pdf. Adopted 27 September 2007; reprinted April 2018; accessed 8 March 2025. [↗](https://psychology.org.au/getmedia/)
4. Pablo Ascorbe, María S Campos, César Domínguez, Jónathan Heras, Magdalena Pérez, and Ana Rosa 39579 9 [find](https://scholar.google.com/scholar?q=Pablo+Ascorbe%2C+Mar%C3%ADa+S+Campos%2C+C%C3%A9sar+Dom%C3%ADnguez%2C+J%C3%B3nathan+Heras%2C+Magdalena+P%C3%A9rez%2C+and+Ana+Rosa+39579+9)
5. Terroba-Reinares. 2025. A chatbot for providing suicide prevention information in spanish. In Proceedings of the 15th International Workshop on Spoken Dialogue Systems Technology, pages 200–204. [find](https://scholar.google.com/scholar?q=Terroba%2DReinares%2E+2025%2E+A+chatbot+for+providing+suicide+prevention+information+in+spanish%2E+In+Proceedings+of+the+15th+International+Workshop+on+Spoken+Dialogue+Systems+Technology%2C+pages+200%E2%80%93204%2E)
6. Yejin Bang, Delong Chen, Nayeon Lee, and Pascale Fung. 2024. [Measuring political bias in large language models: What is said and how it is said](https://md.research.elamur.ai/free/en/papers/bang-2024-measuring-political-bias-large-language/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11142–11159.
7. Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J Pappas, Florian Tramer, and 1 others. 2024. [Jailbreakbench: An open robustness benchmark for jailbreaking large language models](https://md.research.elamur.ai/free/en/papers/chao-2024-jailbreakbench-open-robustness-benchmark-jailbreaking/). Advances in Neural…
8. Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, and Benyou Wang. 2025a. Towards medical complex reasoning with LLMs through medical verifiable problems. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14552–14573, Vienna, Austria. Associatio… [find](https://scholar.google.com/scholar?q=Junying+Chen%2C+Zhenyang+Cai%2C+Ke+Ji%2C+Xidong+Wang%2C+Wanlong+Liu%2C+Rongsheng+Wang%2C+and+Benyou+Wang%2E+2025a%2E+Towards+medical+complex+reasoning+with+LLMs+through+medical+verifiable+problems%2E+In+Findings+of+the)
9. Tong Chen, Zimu Wang, Yiyi Miao, Haoran Luo, Sun Yuanfei, Wei Wang, Zhengyong Jiang, Procheta Sen, and Jionglong Su. 2025b. MedFact: A large-scale Chinese dataset for evidence-based medical fact-checking of LLM responses. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language… [find](https://scholar.google.com/scholar?q=Tong+Chen%2C+Zimu+Wang%2C+Yiyi+Miao%2C+Haoran+Luo%2C+Sun+Yuanfei%2C+Wei+Wang%2C+Zhengyong+Jiang%2C+Procheta+Sen%2C+and+Jionglong+Su%2E+2025b%2E+MedFact%3A+A+large%2Dscale+Chinese+dataset+for+evidence%2Dbased+medical+fact%2Dcheck)
10. Zeming Chen, Alejandro Hernández Cano, Angelika Romanou, Antoine Bonnet, Kyle Matoba, Francesco Salvi, Matteo Pagliardini, Simin Fan, Andreas Köpf, Amirkeivan Mohtashami, Alexandre Sallinen, Alireza Sakhaeirad, Vinitra Swamy, Igor Krawczuk, Deniz Bayazit, Axel Marmet, Syrielle Montariol, Mary-Anne H… — [MEDITRON-70B: Scaling Medical Pretraining for Large Language Models](https://md.research.elamur.ai/free/en/papers/chen-2023-meditron-70b-scaling-medical-pretraining/)
11. Clément Christophe, Praveen K Kanithi, Tathagata Raha, Shadab Khan, and Marco AF Pimentel. 2024. Med42-v2: A suite of clinical llms. [find](https://scholar.google.com/scholar?q=Cl%C3%A9ment+Christophe%2C+Praveen+K+Kanithi%2C+Tathagata+Raha%2C+Shadab+Khan%2C+and+Marco+AF+Pimentel%2E+2024%2E+Med42%2Dv2%3A+A+suite+of+clinical+llms%2E)
12. Fangjun Ding, Renyu Zhang, Xinyu Feng, Chengye Xie, Zheng Zhang, and Yanting Zhang. 2025. Psylite technical report. Preprint, arXiv:2506.21536. — [arXiv:2506.21536](https://arxiv.org/abs/2506.21536) [find](https://scholar.google.com/scholar?q=Fangjun+Ding%2C+Renyu+Zhang%2C+Xinyu+Feng%2C+Chengye+Xie%2C+Zheng+Zhang%2C+and+Yanting+Zhang%2E+2025%2E+Psylite+technical+report%2E+Preprint%2C+arXiv%3A2506%2E21536%2E+%E2%80%94+%5BarXiv%3A2506%2E21536%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2506%2E21536%29)
13. Jessica Maria Echterhoff, Yao Liu, Abeer Alessa, Julian McAuley, and Zexue He. 2024. Cognitive bias in decision-making with LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12640–12653, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jessica+Maria+Echterhoff%2C+Yao+Liu%2C+Abeer+Alessa%2C+Julian+McAuley%2C+and+Zexue+He%2E+2024%2E+Cognitive+bias+in+decision%2Dmaking+with+LLMs%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+20)
14. Stephanie Fong, Zimu Wang, Guilherme C Oliveira, Xiangyu Zhao, Yiwen Jiang, Jiahe Liu, Beau-Luke Colton, Scott W. Woods, Martha Shenton, Barnaby Nelson, Zongyuan Ge, and Dominic Dwyer. 2026. CHiRPE: A step towards real-world clinical NLP with clinician-oriented model explanations. In Proceedings of… [find](https://scholar.google.com/scholar?q=Stephanie+Fong%2C+Zimu+Wang%2C+Guilherme+C+Oliveira%2C+Xiangyu+Zhao%2C+Yiwen+Jiang%2C+Jiahe+Liu%2C+Beau%2DLuke+Colton%2C+Scott+W%2E+Woods%2C+Martha+Shenton%2C+Barnaby+Nelson%2C+Zongyuan+Ge%2C+and+Dominic+Dwyer%2E+2026%2E+CHiRPE%3A+A)
15. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — [The Llama 3 Herd of Models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/)
16. Chenlu Guo, Nuo Xu, Yi Chang, and Yuan Wu. 2025. Chbench: A chinese dataset for evaluating health in large language models. Preprint, arXiv:2409.15766. — [arXiv:2409.15766](https://arxiv.org/abs/2409.15766) [find](https://scholar.google.com/scholar?q=Chenlu+Guo%2C+Nuo+Xu%2C+Yi+Chang%2C+and+Yuan+Wu%2E+2025%2E+Chbench%3A+A+chinese+dataset+for+evaluating+health+in+large+language+models%2E+Preprint%2C+arXiv%3A2409%2E15766%2E+%E2%80%94+%5BarXiv%3A2409%2E15766%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2409%2E)
17. Tessa Han, Aounon Kumar, Chirag Agarwal, and Himabindu Lakkaraju. 2024. Medsafetybench: Evaluating and improving the medical safety of large language models. Advances in Neural Information Processing Systems, 37:33423–33454. [find](https://scholar.google.com/scholar?q=Tessa+Han%2C+Aounon+Kumar%2C+Chirag+Agarwal%2C+and+Himabindu+Lakkaraju%2E+2024%2E+Medsafetybench%3A+Evaluating+and+improving+the+medical+safety+of+large+language+models%2E+Advances+in+Neural+Information+Processing+)
18. He Hu, Yucheng Zhou, Juzheng Si, Qianning Wang, Hengheng Zhang, Fuji Ren, Fei Ma, Laizhong Cui, and Qi Tian. 2025a. Beyond empathy: Integrating diagnostic and therapeutic reasoning with large language models for mental health counseling. Preprint, arXiv:2505.15715. — [arXiv:2505.15715](https://arxiv.org/abs/2505.15715) [find](https://scholar.google.com/scholar?q=He+Hu%2C+Yucheng+Zhou%2C+Juzheng+Si%2C+Qianning+Wang%2C+Hengheng+Zhang%2C+Fuji+Ren%2C+Fei+Ma%2C+Laizhong+Cui%2C+and+Qi+Tian%2E+2025a%2E+Beyond+empathy%3A+Integrating+diagnostic+and+therapeutic+reasoning+with+large+language)
19. He Hu, Yucheng Zhou, Qianning Wang, Yingjian Zou, Chiyuan Ma, Juzheng Si, Jianzhuang Liu, Zitong Yu, Laizhong Cui, and Fei Ma. 2025b. From pattern recognizers to personalized companions: A survey of large language models in mental health. [find](https://scholar.google.com/scholar?q=He+Hu%2C+Yucheng+Zhou%2C+Qianning+Wang%2C+Yingjian+Zou%2C+Chiyuan+Ma%2C+Juzheng+Si%2C+Jianzhuang+Liu%2C+Zitong+Yu%2C+Laizhong+Cui%2C+and+Fei+Ma%2E+2025b%2E+From+pattern+recognizers+to+personalized+companions%3A+A+survey+of+l)
20. Jinpeng Hu, Tengteng Dong, Gang Luo, Hui Ma, Peng Zou, Xiao Sun, Dan Guo, Xun Yang, and Meng Wang. 2025c. Psycollm: Enhancing llm for psychological understanding and evaluation. IEEE Transactions on Computational Social Systems, 12(2):539–551. [find](https://scholar.google.com/scholar?q=Jinpeng+Hu%2C+Tengteng+Dong%2C+Gang+Luo%2C+Hui+Ma%2C+Peng+Zou%2C+Xiao+Sun%2C+Dan+Guo%2C+Xun+Yang%2C+and+Meng+Wang%2E+2025c%2E+Psycollm%3A+Enhancing+llm+for+psychological+understanding+and+evaluation%2E+IEEE+Transactions+on+C)
21. Jinpeng Hu, Hongchang Shi, Chongyuan Dai, Zhuo Li, Peipei Song, and Meng Wang. 2025d. Beyond emotion recognition: A multi-turn multimodal emotion understanding and reasoning benchmark. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 5814–5823. [find](https://scholar.google.com/scholar?q=Jinpeng+Hu%2C+Hongchang+Shi%2C+Chongyuan+Dai%2C+Zhuo+Li%2C+Peipei+Song%2C+and+Meng+Wang%2E+2025d%2E+Beyond+emotion+recognition%3A+A+multi%2Dturn+multimodal+emotion+understanding+and+reasoning+benchmark%2E+In+Proceedings+)
22. Jinpeng Hu, Ao Wang, Qianqian Xie, Hui Ma, Zhuo Li, and Dan Guo. 2025e. Agentmental: An interactive multi-agent framework for explainable and adaptive mental health assessment. arXiv preprint arXiv:2508.11567. — [arXiv:2508.11567](https://arxiv.org/abs/2508.11567) [find](https://scholar.google.com/scholar?q=Jinpeng+Hu%2C+Ao+Wang%2C+Qianqian+Xie%2C+Hui+Ma%2C+Zhuo+Li%2C+and+Dan+Guo%2E+2025e%2E+Agentmental%3A+An+interactive+multi%2Dagent+framework+for+explainable+and+adaptive+mental+health+assessment%2E+arXiv+preprint+arXiv%3A25)
23. Yining Hua, Hongbin Na, Zehan Li, Fenglin Liu, Xiao Fang, David Clifton, and John Torous. 2025. A scoping review of large language models for generative tasks in mental health care. npj Digital Medicine, 8(1):230. 39580 10 [find](https://scholar.google.com/scholar?q=Yining+Hua%2C+Hongbin+Na%2C+Zehan+Li%2C+Fenglin+Liu%2C+Xiao+Fang%2C+David+Clifton%2C+and+John+Torous%2E+2025%2E+A+scoping+review+of+large+language+models+for+generative+tasks+in+mental+health+care%2E+npj+Digital+Medici)
24. Dongjin Kang, Sunghwan Kim, Taeyoon Kwon, Seungjun Moon, Hyunsouk Cho, Youngjae Yu, Dongha Lee, and Jinyoung Yeo. 2024. Can large language models be good emotional supporter? mitigating preference bias on emotional support conversation. In Proceedings of the 62nd Annual Meeting of the Association fo… [find](https://scholar.google.com/scholar?q=Dongjin+Kang%2C+Sunghwan+Kim%2C+Taeyoon+Kwon%2C+Seungjun+Moon%2C+Hyunsouk+Cho%2C+Youngjae+Yu%2C+Dongha+Lee%2C+and+Jinyoung+Yeo%2E+2024%2E+Can+large+language+models+be+good+emotional+supporter%3F+mitigating+preference+bia)
25. Suyeon Lee, Sunghwan Kim, Minju Kim, Dongjin Kang, Dongil Yang, Harim Kim, Minseok Kang, Dayi Jung, Min Hee Kim, Seungbeen Lee, Kyong-Mee Chung, Youngjae Yu, Dongha Lee, and Jinyoung Yeo. 2024. Cactus: Towards psychological counseling conversations using cognitive behavioral theory. In Findings of t… [find](https://scholar.google.com/scholar?q=Suyeon+Lee%2C+Sunghwan+Kim%2C+Minju+Kim%2C+Dongjin+Kang%2C+Dongil+Yang%2C+Harim+Kim%2C+Minseok+Kang%2C+Dayi+Jung%2C+Min+Hee+Kim%2C+Seungbeen+Lee%2C+Kyong%2DMee+Chung%2C+Youngjae+Yu%2C+Dongha+Lee%2C+and+Jinyoung+Yeo%2E+2024%2E+Cactus)
26. Xiaogeng Liu, Peiran Li, G. Edward Suh, Yevgeniy Vorobeychik, Zhuoqing Mao, Somesh Jha, Patrick McDaniel, Huan Sun, Bo Li, and Chaowei Xiao. 2025. AutoDAN-turbo: A lifelong agent for strategy self-exploration to jailbreak LLMs. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Xiaogeng+Liu%2C+Peiran+Li%2C+G%2E+Edward+Suh%2C+Yevgeniy+Vorobeychik%2C+Zhuoqing+Mao%2C+Somesh+Jha%2C+Patrick+McDaniel%2C+Huan+Sun%2C+Bo+Li%2C+and+Chaowei+Xiao%2E+2025%2E+AutoDAN%2Dturbo%3A+A+lifelong+agent+for+strategy+self%2Dexp)
27. Xiaogeng Liu, Nan Xu, Muhao Chen, and Chaowei Xiao. 2024a. [Autodan: Generating stealthy jailbreak prompts on aligned large language models](https://md.research.elamur.ai/free/en/papers/liu-2023-autodan-generating-stealthy-jailbreak-prompts/). In The Twelfth International Conference on Learning Representations (ICLR).
28. Zhiwei Liu, Kailai Yang, Qianqian Xie, Tianlin Zhang, and Sophia Ananiadou. 2024b. Emollms: A series of emotional large language models and annotation tools for comprehensive affective analysis. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’24, page 54… [find](https://scholar.google.com/scholar?q=Zhiwei+Liu%2C+Kailai+Yang%2C+Qianqian+Xie%2C+Tianlin+Zhang%2C+and+Sophia+Ananiadou%2E+2024b%2E+Emollms%3A+A+series+of+emotional+large+language+models+and+annotation+tools+for+comprehensive+affective+analysis%2E+In+Pr)
29. Jiayuan Ma, Hongbin Na, Zimu Wang, Yining Hua, Yue Liu, Wei Wang, and Ling Chen. 2025. Detecting conversational mental manipulation with intent-aware prompting. In Proceedings of the 31st International Conference on Computational Linguistics, pages 9176–9183, Abu Dhabi, UAE. Association for Computat… [find](https://scholar.google.com/scholar?q=Jiayuan+Ma%2C+Hongbin+Na%2C+Zimu+Wang%2C+Yining+Hua%2C+Yue+Liu%2C+Wei+Wang%2C+and+Ling+Chen%2E+2025%2E+Detecting+conversational+mental+manipulation+with+intent%2Daware+prompting%2E+In+Proceedings+of+the+31st+Internationa)
30. Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li, and 1 others. 2024. [Harmbench: A standardized evaluation framework for automated red teaming and robust refusal](https://md.research.elamur.ai/free/en/papers/mazeika-2024-harmbench-standardized-evaluation-framework-automated/). In International Conference on Machine Learning, pages 35181–352…
31. Hongbin Na, Yining Hua, Zimu Wang, Tao Shen, Beibei Yu, Lilin Wang, Wei Wang, John Torous, and Ling Chen. 2025a. A survey of large language models in psychotherapy: Current landscape and future directions. [find](https://scholar.google.com/scholar?q=Hongbin+Na%2C+Yining+Hua%2C+Zimu+Wang%2C+Tao+Shen%2C+Beibei+Yu%2C+Lilin+Wang%2C+Wei+Wang%2C+John+Torous%2C+and+Ling+Chen%2E+2025a%2E+A+survey+of+large+language+models+in+psychotherapy%3A+Current+landscape+and+future+direct)
32. Hongbin Na, Zimu Wang, Zhaoming Chen, Peilin Zhou, Yining Hua, Grace Ziqi Zhou, Haiyang Zhang, Tao Shen, Wei Wang, John Torous, Shaoxiong Ji, and Ling Chen. 2025b. [You never know a person, you only know their defenses: Detecting levels of psychological defense mechanisms in supportive conversations](https://md.research.elamur.ai/free/en/papers/na-2026-you-never-know-person-you/).…
33. OpenAI. 2025. Gpt-5 system card. Technical report, OpenAI. Accessed: 2025-01-01. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Gpt%2D5+system+card%2E+Technical+report%2C+OpenAI%2E+Accessed%3A+2025%2D01%2D01%2E)
34. Nadine J. Pelling and Lorelle J. Burton, editors. 2017. The Elements of Applied Psychological Practice in Australia: Preparing for the National Psychology Examination. Routledge, Abingdon, Oxon and New York, NY. Edited volume. [find](https://scholar.google.com/scholar?q=Nadine+J%2E+Pelling+and+Lorelle+J%2E+Burton%2C+editors%2E+2017%2E+The+Elements+of+Applied+Psychological+Practice+in+Australia%3A+Preparing+for+the+National+Psychology+Examination%2E+Routledge%2C+Abingdon%2C+Oxon+and+Ne)
35. 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!](https://md.research.elamur.ai/free/en/papers/qi-2023-fine-tuning-aligned-language-models/) In The Twelfth International Conference on Learning Representations (ICLR).
36. Huachuan Qiu, Anqi Li, Lizhi Ma, and Zhenzhong Lan. 2024a. Psychat: A client-centric dialogue system for mental health support. In 2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pages 2979–2984. [find](https://scholar.google.com/scholar?q=Huachuan+Qiu%2C+Anqi+Li%2C+Lizhi+Ma%2C+and+Zhenzhong+Lan%2E+2024a%2E+Psychat%3A+A+client%2Dcentric+dialogue+system+for+mental+health+support%2E+In+2024+27th+International+Conference+on+Computer+Supported+Cooperative+)
37. Huachuan Qiu, Lizhi Ma, and Zhenzhong Lan. 2024b. PsyGUARD: An automated system for suicide detection and risk assessment in psychological counseling. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4581–4607, Miami, Florida, USA. Association for Comp… [find](https://scholar.google.com/scholar?q=Huachuan+Qiu%2C+Lizhi+Ma%2C+and+Zhenzhong+Lan%2E+2024b%2E+PsyGUARD%3A+An+automated+system+for+suicide+detection+and+risk+assessment+in+psychological+counseling%2E+In+Proceedings+of+the+2024+Conference+on+Empirica)
38. Huachuan Qiu, Tong Zhao, Anqi Li, Shuai Zhang, Hongliang He, and Zhenzhong Lan. 2023. A benchmark for understanding dialogue safety in mental health support. page 1–13, Berlin, Heidelberg. Springer-Verlag. [find](https://scholar.google.com/scholar?q=Huachuan+Qiu%2C+Tong+Zhao%2C+Anqi+Li%2C+Shuai+Zhang%2C+Hongliang+He%2C+and+Zhenzhong+Lan%2E+2023%2E+A+benchmark+for+understanding+dialogue+safety+in+mental+health+support%2E+page+1%E2%80%9313%2C+Berlin%2C+Heidelberg%2E+Springer%2DVe)
39. Jiahao Qiu, Yinghui He, Xinzhe Juan, Yimin Wang, Yuhan Liu, Zixin Yao, Yue Wu, Xun Jiang, Ling Yang, and Mengdi Wang. 2025. EmoAgent: Assessing and safeguarding human-AI interaction for mental health safety. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, p… [find](https://scholar.google.com/scholar?q=Jiahao+Qiu%2C+Yinghui+He%2C+Xinzhe+Juan%2C+Yimin+Wang%2C+Yuhan+Liu%2C+Zixin+Yao%2C+Yue+Wu%2C+Xun+Jiang%2C+Ling+Yang%2C+and+Mengdi+Wang%2E+2025%2E+EmoAgent%3A+Assessing+and+safeguarding+human%2DAI+interaction+for+mental+health+)
40. RANZCP. 2016. Ranzcp code of conduct. [https://www.ranzcp.org/getmedia/](https://www.ranzcp.org/getmedia/) 687dfad7-1675-4fdb-ae29-2cf4c1d930eb/ Code-of-Conduct-RANZCP.pdf. Accessed: 8 March 2025. [↗](https://www.ranzcp.org/getmedia/)
41. RANZCP. 2018. Ranzcp code of ethics. [https://www.ranzcp.org/getmedia/](https://www.ranzcp.org/getmedia/) 2e090981-cdd2-4dee-a317-f8718bc7dc47/ Code-of-Ethics-Aug-2025.pdf. Fifth edition; published 2018; accessed 8 March 2025. 39581 11 [↗](https://www.ranzcp.org/getmedia/)
42. Peipei Song, Dan Guo, Xun Yang, Shengeng Tang, and Meng Wang. 2024. Emotional video captioning with vision-based emotion interpretation network. IEEE Transactions on Image Processing, 33:1122–1135. [find](https://scholar.google.com/scholar?q=Peipei+Song%2C+Dan+Guo%2C+Xun+Yang%2C+Shengeng+Tang%2C+and+Meng+Wang%2E+2024%2E+Emotional+video+captioning+with+vision%2Dbased+emotion+interpretation+network%2E+IEEE+Transactions+on+Image+Processing%2C+33%3A1122%E2%80%931135%2E)
43. 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, and 49 others… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
44. Doan Nam Long Vu, Rui Tan, Lena Moench, Svenja Jule Francke, Daniel Woiwod, Florian Thomas-Odenthal, Sanna Stroth, Tilo Kircher, Christiane Hermann, Udo Dannlowski, Hamidreza Ja-malabadi, and Shaoxiong Ji. 2025. Roleplaying with structure: Synthetic therapist-client conversation generation from ques… — [arXiv:2510.25384](https://arxiv.org/abs/2510.25384) [find](https://scholar.google.com/scholar?q=Doan+Nam+Long+Vu%2C+Rui+Tan%2C+Lena+Moench%2C+Svenja+Jule+Francke%2C+Daniel+Woiwod%2C+Florian+Thomas%2DOdenthal%2C+Sanna+Stroth%2C+Tilo+Kircher%2C+Christiane+Hermann%2C+Udo+Dannlowski%2C+Hamidreza+Ja%2Dmalabadi%2C+and+Shaoxion)
45. Bingning Wang, Haizhou Zhao, Huozhi Zhou, Liang Song, Mingyu Xu, Wei Cheng, Xiangrong Zeng, Yupeng Zhang, Yuqi Huo, Zecheng Wang, Zhengyun Zhao, Da Pan, Fei Kou, Fei Li, Fuzhong Chen, Guosheng Dong, Han Liu, Hongda Zhang, Jin He, and 23 others. 2025a. [Baichuan-m1: Pushing the medical capability of l…](https://md.research.elamur.ai/free/en/papers/wang-2025-baichuan-m1-pushing-medical/)
46. Shiquan Wang, Ruiyu Fang, Zhongjiang He, Shuangyong Song, and Yongxiang Li. 2025b. Emotional support with llm-based empathetic dialogue generation. Preprint, arXiv:2507.12820. — [arXiv:2507.12820](https://arxiv.org/abs/2507.12820) [find](https://scholar.google.com/scholar?q=Shiquan+Wang%2C+Ruiyu+Fang%2C+Zhongjiang+He%2C+Shuangyong+Song%2C+and+Yongxiang+Li%2E+2025b%2E+Emotional+support+with+llm%2Dbased+empathetic+dialogue+generation%2E+Preprint%2C+arXiv%3A2507%2E12820%2E+%E2%80%94+%5BarXiv%3A2507%2E12820%5D%28htt)
47. Synthia Wang, Yuwei Cheng, Austin Song, Sarah Keedy, Marc Berman, and Nick Feamster. 2025c. Can llms address mental health questions? a comparison with human therapists. Preprint, arXiv:2509.12102. — [arXiv:2509.12102](https://arxiv.org/abs/2509.12102) [find](https://scholar.google.com/scholar?q=Synthia+Wang%2C+Yuwei+Cheng%2C+Austin+Song%2C+Sarah+Keedy%2C+Marc+Berman%2C+and+Nick+Feamster%2E+2025c%2E+Can+llms+address+mental+health+questions%3F+a+comparison+with+human+therapists%2E+Preprint%2C+arXiv%3A2509%2E12102%2E+%E2%80%94+)
48. Jianhui Wei, Zijie Meng, Zikai Xiao, Tianxiang Hu, Yang Feng, Zhijie Zhou, Jian Wu, and Zuozhu Liu. 2025. Medethicsqa: A comprehensive question answering benchmark for medical ethics evaluation of llms. Preprint, arXiv:2506.22808. — [arXiv:2506.22808](https://arxiv.org/abs/2506.22808) [find](https://scholar.google.com/scholar?q=Jianhui+Wei%2C+Zijie+Meng%2C+Zikai+Xiao%2C+Tianxiang+Hu%2C+Yang+Feng%2C+Zhijie+Zhou%2C+Jian+Wu%2C+and+Zuozhu+Liu%2E+2025%2E+Medethicsqa%3A+A+comprehensive+question+answering+benchmark+for+medical+ethics+evaluation+of+llm)
49. Zheyong Xie, Shaosheng Cao, Zuozhu Liu, Zheyu Ye, Zihan Niu, Chonggang Lu, Tong Xu, Enhong Chen, Zhe Xu, Yao Hu, and Wei Lu. 2025. iPET: An interactive emotional companion dialogue system with LLM-powered virtual pet world simulation. In Proceedings of the 63rd Annual Meeting of the Association for… [find](https://scholar.google.com/scholar?q=Zheyong+Xie%2C+Shaosheng+Cao%2C+Zuozhu+Liu%2C+Zheyu+Ye%2C+Zihan+Niu%2C+Chonggang+Lu%2C+Tong+Xu%2C+Enhong+Chen%2C+Zhe+Xu%2C+Yao+Hu%2C+and+Wei+Lu%2E+2025%2E+iPET%3A+An+interactive+emotional+companion+dialogue+system+with+LLM%2Dpow)
50. Ancheng Xu, Di Yang, Renhao Li, Jingwei Zhu, Minghuan Tan, Min Yang, Wanxin Qiu, Mingchen Ma, Haihong Wu, Bingyu Li, Feng Sha, Chengming Li, Xiping Hu, Qiang Qu, Derek F. Wong, and Ruifeng Xu. 2025a. Autocbt: An autonomous multi-agent framework for cognitive behavioral therapy in psychological couns… — [arXiv:2501.09426](https://arxiv.org/abs/2501.09426) [find](https://scholar.google.com/scholar?q=Ancheng+Xu%2C+Di+Yang%2C+Renhao+Li%2C+Jingwei+Zhu%2C+Minghuan+Tan%2C+Min+Yang%2C+Wanxin+Qiu%2C+Mingchen+Ma%2C+Haihong+Wu%2C+Bingyu+Li%2C+Feng+Sha%2C+Chengming+Li%2C+Xiping+Hu%2C+Qiang+Qu%2C+Derek+F%2E+Wong%2C+and+Ruifeng+Xu%2E+2025a%2E+)
51. Yangyang Xu, Jinpeng Hu, Zhuoer Zhao, Zhangling Duan, Xiao Sun, and Xun Yang. 2025b. Multiagentesc: A llm-based multi-agent collaboration framework for emotional support conversation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 4665–4681. [find](https://scholar.google.com/scholar?q=Yangyang+Xu%2C+Jinpeng+Hu%2C+Zhuoer+Zhao%2C+Zhangling+Duan%2C+Xiao+Sun%2C+and+Xun+Yang%2E+2025b%2E+Multiagentesc%3A+A+llm%2Dbased+multi%2Dagent+collaboration+framework+for+emotional+support+conversation%2E+In+Proceedings+o)
52. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, and 40 others. 2024a. Qwen2 technical report. arXiv preprint arX… [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Guanting+Dong%2C+Haoran+Wei%2C+Huan+Lin%2C+Jialong+Tang%2C+Jialin+Wang%2C+Jian+Yang%2C+Jian)
53. Haoran Yang, Yumeng Zhang, Jiaqi Xu, Hongyuan Lu, Pheng-Ann Heng, and Wai Lam. 2024b. Unveiling the generalization power of fine-tuned large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolog… [find](https://scholar.google.com/scholar?q=Haoran+Yang%2C+Yumeng+Zhang%2C+Jiaqi+Xu%2C+Hongyuan+Lu%2C+Pheng%2DAnn+Heng%2C+and+Wai+Lam%2E+2024b%2E+Unveiling+the+generalization+power+of+fine%2Dtuned+large+language+models%2E+In+Proceedings+of+the+2024+Conference+of+t)
54. Kailai Yang, Tianlin Zhang, Ziyan Kuang, Qianqian Xie, Jimin Huang, and Sophia Ananiadou. 2024c. Mentallama: interpretable mental health analysis on social media with large language models. In Proceedings of the ACM Web Conference 2024, pages 4489–4500. [find](https://scholar.google.com/scholar?q=Kailai+Yang%2C+Tianlin+Zhang%2C+Ziyan+Kuang%2C+Qianqian+Xie%2C+Jimin+Huang%2C+and+Sophia+Ananiadou%2E+2024c%2E+Mentallama%3A+interpretable+mental+health+analysis+on+social+media+with+large+language+models%2E+In+Proceed)
55. Jing Ye, Lu Xiang, Yaping Zhang, and Chengqing Zong. 2024. [Sweetiechat: A strategy-enhanced role-playing framework for diverse scenarios handling emotional support agent](https://md.research.elamur.ai/free/en/papers/ye-2025-sweetiechat-strategy-enhanced-role-playing/). Preprint, arXiv:2412.08389.
56. Tenggan Zhang, Xinjie Zhang, Jinming Zhao, Li Zhou, and Qin Jin. 2024a. ESCoT: Towards interpretable emotional support dialogue systems. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13395–13412, Bangkok, Thailand. Associati… [find](https://scholar.google.com/scholar?q=Tenggan+Zhang%2C+Xinjie+Zhang%2C+Jinming+Zhao%2C+Li+Zhou%2C+and+Qin+Jin%2E+2024a%2E+ESCoT%3A+Towards+interpretable+emotional+support+dialogue+systems%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+fo)
57. Zhexin Zhang, Leqi Lei, Lindong Wu, Rui Sun, Yongkang Huang, Chong Long, Xiao Liu, Xuanyu Lei, Jie Tang, and Minlie Huang. 2024b. Safety-Bench: Evaluating the safety of large language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long P… [find](https://scholar.google.com/scholar?q=Zhexin+Zhang%2C+Leqi+Lei%2C+Lindong+Wu%2C+Rui+Sun%2C+Yongkang+Huang%2C+Chong+Long%2C+Xiao+Liu%2C+Xuanyu+Lei%2C+Jie+Tang%2C+and+Minlie+Huang%2E+2024b%2E+Safety%2DBench%3A+Evaluating+the+safety+of+large+language+models%2E+In+Proce)
58. Xiangyu Zhao, Yaling Shen, Yiwen Jiang, Zimu Wang, Jiahe Liu, Maxmartwell H Cheng, Guilherme C Oliveira, Robert Desimone, Dominic Dwyer, and Zongyuan Ge. 2025. It hears, it sees too: Multimodal llm for depression detection by integrating visual understanding into audio language models. Preprint, arX… — [arXiv:2511.19877](https://arxiv.org/abs/2511.19877) [find](https://scholar.google.com/scholar?q=Xiangyu+Zhao%2C+Yaling+Shen%2C+Yiwen+Jiang%2C+Zimu+Wang%2C+Jiahe+Liu%2C+Maxmartwell+H+Cheng%2C+Guilherme+C+Oliveira%2C+Robert+Desimone%2C+Dominic+Dwyer%2C+and+Zongyuan+Ge%2E+2025%2E+It+hears%2C+it+sees+too%3A+Multimodal+llm+fo)
59. Jinfeng Zhou, Yuxuan Chen, Jianing Yin, Yongkang Huang, Yihan Shi, Xikun Zhang, Libiao Peng, Rongsheng Zhang, Tangjie Lv, Zhipeng Hu, Hongning 39582 12 [find](https://scholar.google.com/scholar?q=Jinfeng+Zhou%2C+Yuxuan+Chen%2C+Jianing+Yin%2C+Yongkang+Huang%2C+Yihan+Shi%2C+Xikun+Zhang%2C+Libiao+Peng%2C+Rongsheng+Zhang%2C+Tangjie+Lv%2C+Zhipeng+Hu%2C+Hongning+39582+12)
60. Wang, and Minlie Huang. 2025. [Crisp: Cognitive restructuring of negative thoughts through multi-turn supportive dialogues](https://md.research.elamur.ai/free/en/papers/zhou-2025-crisp-cognitive-restructuring-negative-thoughts/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: EMNLP 2025, pages 32462– 32491, Suzhou, China. Association for Computational Linguisti…
61. Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, and Matt Fredrikson. 2023. [Universal and transferable adversarial attacks on aligned language models](https://md.research.elamur.ai/free/en/papers/zou-2023-universal-transferable-adversarial-attacks-aligned/). Preprint, arXiv:2307.15043.

*Updated 1 November 2026*