---
title: "CARE-CR — paper by Qi et al. (2026) — summary and ideas"
description: "CARE-CR addresses automated cognitive restructuring with LLMs. 48.06% F1. 46 references."
authors: ["Hongzhi Qi", "Liangcheng Wang", "Yijing YU", "Jianqiang Li", "Bing Xiang Yang", "Qing Zhao"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1030/"
doi: "10.18653/v1/2026.findings-acl.1030"
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/qi-2026-care-cr-context-aware-routing/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/qi-2026-care-cr-context-aware-routing/)

[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/26/) / CARE-CR: Context-Aware Routing and Expert Fusion for Multi-Preference Cognitive Restructuring

# CARE-CR: Context-Aware Routing and Expert Fusion for Multi-Preference Cognitive Restructuring

**Authors:** Hongzhi Qi, Liangcheng Wang, Yijing YU, Jianqiang Li, Bing Xiang Yang and Qing Zhao · **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.1030/) · [PDF](https://aclanthology.org/2026.findings-acl.1030.pdf) · [DOI 10.18653/v1/2026.findings-acl.1030](https://doi.org/10.18653/v1/2026.findings-acl.1030) · [OpenAlex](https://openalex.org/W7166821071)

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

## Summary
CARE-CR addresses automated cognitive restructuring with LLMs. Existing systems tend to produce generic positive rewrites, skip explicit diagnosis of the distorted belief, and handle conflicting therapeutic goals such as empathy and rationality through one fixed objective. Grounded in Ellis's ABCD model, the authors treat the task as two steps: identify cognitive distortions in a distress narrative, then generate a disputation. Because the right balance of therapeutic qualities depends on the situation, they predict a preference vector for each input instead of optimizing one global reward.

The pipeline has four parts:
- separate reward models and expert policies for each restructuring dimension;
- a hierarchical, dimension-guided MCTS (DG-HMCTS) that generates extra preference pairs when expert supervision is scarce;
- a routing predictor that outputs context-dependent weights;
- weight-space merging of the expert policies, which also lets users adjust the output.

The authors report gains over strong baselines in diagnosis, contextual fit, task effectiveness and helpfulness. They also release the dataset and code. The work matters because it shows a route to restructuring that is controllable and diagnosis-driven rather than cosmetic, though no clinical validation has been done yet.

## Key points
- **Experts and fusion:** There are six dimension-specific frozen reward models and matching expert policies. At inference, the policies are combined by adding weighted parameter deltas to a reference model. The final weights mix clinician-predicted and user-provided preferences, balanced by a parameter α.
- **Diagnosis result:** The full system reaches 48.06% F1 on distortion recognition. In ablations, removing context-aware routing lowers this to 46.15, and an SFT-only variant lowers it to 43.14. The SFT-only variant scores higher on BLEU/ROUGE but has much lower diversity (Dist-2 of 6.96 vs 19.50).
- **Encoder baselines:** Fine-tuned encoders such as BERT, DeBERTaV3, ERNIE 3.0 and Chinese MentalBERT hit similar ceilings. Chinese MentalBERT trained with extra C2D2 samples reaches 50.99 F1, which suggests distortion detection is still hard.
- **Limitations:** The system uses text only and is evaluated on single turns. The search and fusion steps add computational cost.
- **Ethics and availability:** The data collection was IRB-approved (WHU-LFMD-IRB2025043), and code and data are on GitHub (HongzhiQ/CARE-CR).

*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

- [Wuhan University](https://md.research.elamur.ai/free/en/universities/wuhan-university/) — University, Wuhan, China · 47 works · 1,246 citations
- [Beijing University of Technology](https://md.research.elamur.ai/free/en/universities/beijing-university-of-technology/) — University, Beijing, China · 16 works · 1,910 citations

📚 Shelves (4): [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Social Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · 330 works · [💭 Clinical Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/clinical-psychology/) · 21 works · [💭 Applied Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/applied-psychology/) · 25 works

## Cite

Cite as: Hongzhi Qi, Liangcheng Wang, Yijing YU, Jianqiang Li, Bing Xiang Yang and Qing Zhao. 2026. CARE-CR: Context-Aware Routing and Expert Fusion for Multi-Preference Cognitive Restructuring. 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{qi2026care,
  title = {{CARE-CR: Context-Aware Routing and Expert Fusion for Multi-Preference Cognitive Restructuring}},
  author = {Hongzhi Qi, Liangcheng Wang, Yijing YU, Jianqiang Li, Bing Xiang Yang and Qing Zhao},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1030},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1030}
}
```

- [← previous Cards Against Contamination: TCG-Bench for Difficulty-Scalable Multilingual LLM Reasoning](https://md.research.elamur.ai/free/en/papers/alrashed-2026-cards-against-contamination-tcg-bench/)
- [next → Carefully Considering Culture: Analyzing LLM Alignment in Single- and Multi-Cultural Settings using Cultural Consensus Theory](https://md.research.elamur.ai/free/en/papers/pothugunta-2026-carefully-considering-culture-analyzing-llm/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/26/)

## References

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

1. Mari Aguilera, Clara Paz, Victoria Compañ, Juan Carlos Medina, and Guillem Feixas. 2019. Cognitive rigidity in patients with depression and fibromyalgia. International journal of clinical and health psychology, 19(2):160–164. [find](https://scholar.google.com/scholar?q=Mari+Aguilera%2C+Clara+Paz%2C+Victoria+Compa%C3%B1%2C+Juan+Carlos+Medina%2C+and+Guillem+Feixas%2E+2019%2E+Cognitive+rigidity+in+patients+with+depression+and+fibromyalgia%2E+International+journal+of+clinical+and+health+p)
2. André Aleman and Damiaan Denys. 2014. Mental health: a road map for suicide research and prevention. Nature, 509(7501):421–423. [find](https://scholar.google.com/scholar?q=Andr%C3%A9+Aleman+and+Damiaan+Denys%2E+2014%2E+Mental+health%3A+a+road+map+for+suicide+research+and+prevention%2E+Nature%2C+509%287501%29%3A421%E2%80%93423%2E)
3. David D Burns. 1981. Feeling good. Signet Book. [find](https://scholar.google.com/scholar?q=David+D+Burns%2E+1981%2E+Feeling+good%2E+Signet+Book%2E)
4. Yu Ying Chiu, Ashish Sharma, Inna Wanyin Lin, and Tim Althoff. 2024. A computational framework for behavioral assessment of llm therapists. arXiv preprint arXiv:2401.00820. — [arXiv:2401.00820](https://arxiv.org/abs/2401.00820) [find](https://scholar.google.com/scholar?q=Yu+Ying+Chiu%2C+Ashish+Sharma%2C+Inna+Wanyin+Lin%2C+and+Tim+Althoff%2E+2024%2E+A+computational+framework+for+behavioral+assessment+of+llm+therapists%2E+arXiv+preprint+arXiv%3A2401%2E00820%2E+%E2%80%94+%5BarXiv%3A2401%2E00820%5D%28https%3A)
5. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, et al. 2025. [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/). arXiv prep…
6. Yiming Cui, Ziqing Yang, and Ting Liu. 2022. Pert: pre-training bert with permuted language model. arXiv preprint arXiv:2203.06906. — [arXiv:2203.06906](https://arxiv.org/abs/2203.06906) [find](https://scholar.google.com/scholar?q=Yiming+Cui%2C+Ziqing+Yang%2C+and+Ting+Liu%2E+2022%2E+Pert%3A+pre%2Dtraining+bert+with+permuted+language+model%2E+arXiv+preprint+arXiv%3A2203%2E06906%2E+%E2%80%94+%5BarXiv%3A2203%2E06906%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2203%2E06906%29)
7. Yiming Cui, Ziqing Yang, and Xin Yao. 2023. [Efficient and effective text encoding for chinese llama and alpaca](https://md.research.elamur.ai/free/en/papers/cui-2023-efficient-effective-text-encoding-chinese/). arXiv preprint arXiv:2304.08177.
8. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of NAACL-HLT.
9. Albert Ellis. 1962. Reason and emotion in psychotherapy. [find](https://scholar.google.com/scholar?q=Albert+Ellis%2E+1962%2E+Reason+and+emotion+in+psychotherapy%2E)
10. Shivank Garg, Ayush Singh, Shweta Singh, and Paras Chopra. 2025. Ipo: Your language model is secretly a preference classifier. arXiv preprint arXiv:2502.16182. [find](https://scholar.google.com/scholar?q=Shivank+Garg%2C+Ayush+Singh%2C+Shweta+Singh%2C+and+Paras+Chopra%2E+2025%2E+Ipo%3A+Your+language+model+is+secretly+a+preference+classifier%2E+arXiv+preprint+arXiv%3A2502%2E16182%2E)
11. Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, et al. 2024. [Chatglm: A family of large language models from glm-130b to glm-4 all tools](https://md.research.elamur.ai/free/en/papers/glm-2024-chatglm-family-large-language-models/). arXiv preprint arXiv:2406.12793.
12. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 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/). arXiv preprint arXiv:2501.12948.
13. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2023. [Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing](https://md.research.elamur.ai/free/en/papers/he-2021-debertav3-improving-deberta-using-electra/). In Proceedings of the International Conference on Learning Representations (ICLR) 2023.
14. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). ICLR, 1(2):3.
15. Zainab Iftikhar, Sean Ransom, Amy Xiao, Nicole Nugent, and Jeff Huang. 2024. Therapy as an nlp task: psychologists’ comparison of llms and human peers in cbt. arXiv preprint arXiv:2409.02244. — [arXiv:2409.02244](https://arxiv.org/abs/2409.02244) [find](https://scholar.google.com/scholar?q=Zainab+Iftikhar%2C+Sean+Ransom%2C+Amy+Xiao%2C+Nicole+Nugent%2C+and+Jeff+Huang%2E+2024%2E+Therapy+as+an+nlp+task%3A+psychologists%E2%80%99+comparison+of+llms+and+human+peers+in+cbt%2E+arXiv+preprint+arXiv%3A2409%2E02244%2E+%E2%80%94+%5BarXiv)
16. Eirini Karyotaki and Wouter van Ballegooijen. 2020. Digital self-help interventions for suicidal ideation and behaviour. The Lancet Digital Health, 2(1):e4– e5. [find](https://scholar.google.com/scholar?q=Eirini+Karyotaki+and+Wouter+van+Ballegooijen%2E+2020%2E+Digital+self%2Dhelp+interventions+for+suicidal+ideation+and+behaviour%2E+The+Lancet+Digital+Health%2C+2%281%29%3Ae4%E2%80%93+e5%2E)
17. Subin Kim, Hoonrae Kim, Heejin Do, and Gary Lee. 2025. Multimodal cognitive reframing therapy via multi-hop psychotherapeutic reasoning. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume… [find](https://scholar.google.com/scholar?q=Subin+Kim%2C+Hoonrae+Kim%2C+Heejin+Do%2C+and+Gary+Lee%2E+2025%2E+Multimodal+cognitive+reframing+therapy+via+multi%2Dhop+psychotherapeutic+reasoning%2E+In+Proceedings+of+the+2025+Conference+of+the+Nations+of+the+Ame)
18. Suyeon Lee, Jieun Kang, Harim Kim, Kyoung-Mee Chung, Dongha Lee, and Jinyoung Yeo. 2024. Cocoa: Cbt-based conversational counseling agent using memory specialized in cognitive distortions and dynamic prompt. arXiv preprint arXiv:2402.17546. — [arXiv:2402.17546](https://arxiv.org/abs/2402.17546) [find](https://scholar.google.com/scholar?q=Suyeon+Lee%2C+Jieun+Kang%2C+Harim+Kim%2C+Kyoung%2DMee+Chung%2C+Dongha+Lee%2C+and+Jinyoung+Yeo%2E+2024%2E+Cocoa%3A+Cbt%2Dbased+conversational+counseling+agent+using+memory+specialized+in+cognitive+distortions+and+dynamic+)
19. Chin-Yew Lin. 2004. [Rouge: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text summarization branches out, pages 74–81.
20. Shuya Lin, Yuxiong Wang, Jonathan Dong, and Shiguang Ni. Detection and positive reconstruction of cognitive distortion sentences: Mandarin dataset and evaluation. [find](https://scholar.google.com/scholar?q=Shuya+Lin%2C+Yuxiong+Wang%2C+Jonathan+Dong%2C+and+Shiguang+Ni%2E+Detection+and+positive+reconstruction+of+cognitive+distortion+sentences%3A+Mandarin+dataset+and+evaluation%2E)
21. Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, et al. 2024. [Mitigating the alignment tax of rlhf](https://md.research.elamur.ai/free/en/papers/lin-2024-mitigating-alignment-tax-rlhf/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 580–606.
22. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+et+al%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E19437%2E)
23. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv preprint arXiv:1907.11692.
24. Mounica Maddela, Megan Ung, Jing Xu, Andrea Madotto, Heather Foran, and Y-Lan Boureau. 2023. Training models to generate, recognize, and reframe unhelpful thoughts. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13641– 13660. [find](https://scholar.google.com/scholar?q=Mounica+Maddela%2C+Megan+Ung%2C+Jing+Xu%2C+Andrea+Madotto%2C+Heather+Foran%2C+and+Y%2DLan+Boureau%2E+2023%2E+Training+models+to+generate%2C+recognize%2C+and+reframe+unhelpful+thoughts%2E+In+Proceedings+of+the+61st+Annual+M)
25. Daniel Marta, Simon Holk, Christian Pek, Jana Tumova, and Iolanda Leite. 2023. Aligning human preferences with baseline objectives in reinforcement learning. In IEEE International Conference on Robotics and Automation (ICRA), MAY 29-JUN 02, 2023, London, ENGLAND. Institute of Electrical and Electron… [find](https://scholar.google.com/scholar?q=Daniel+Marta%2C+Simon+Holk%2C+Christian+Pek%2C+Jana+Tumova%2C+and+Iolanda+Leite%2E+2023%2E+Aligning+human+preferences+with+baseline+objectives+in+reinforcement+learning%2E+In+IEEE+International+Conference+on+Roboti)
26. Andrew Mutton, Mark Dras, Stephen Wan, and Robert Dale. 2007. Gleu: Automatic evaluation of sentence-level fluency. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 344–351. [find](https://scholar.google.com/scholar?q=Andrew+Mutton%2C+Mark+Dras%2C+Stephen+Wan%2C+and+Robert+Dale%2E+2007%2E+Gleu%3A+Automatic+evaluation+of+sentence%2Dlevel+fluency%2E+In+Proceedings+of+the+45th+Annual+Meeting+of+the+Association+of+Computational+Lingui)
27. Hongbin Na. 2024. Cbt-llm: A chinese large language model for cognitive behavioral therapy-based mental health question answering. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2930–2940. [find](https://scholar.google.com/scholar?q=Hongbin+Na%2E+2024%2E+Cbt%2Dllm%3A+A+chinese+large+language+model+for+cognitive+behavioral+therapy%2Dbased+mental+health+question+answering%2E+In+Proceedings+of+the+2024+Joint+International+Conference+on+Computat)
28. Jingping Nie, Hanya Shao, Yuang Fan, Qijia Shao, Haoxuan You, Matthias Preindl, and Xiaofan Jiang. Llm-based conversational ai therapist for daily functioning screening and psychotherapeutic intervention via everyday smart devices. ACM Transactions on Computing for Healthcare. [find](https://scholar.google.com/scholar?q=Jingping+Nie%2C+Hanya+Shao%2C+Yuang+Fan%2C+Qijia+Shao%2C+Haoxuan+You%2C+Matthias+Preindl%2C+and+Xiaofan+Jiang%2E+Llm%2Dbased+conversational+ai+therapist+for+daily+functioning+screening+and+psychotherapeutic+intervent)
29. OpenAI. 2024. Gpt-5 model documentation. [https://platform.openai.com/docs/models](https://platform.openai.com/docs/models). [↗](https://platform.openai.com/docs/models)
30. World Health Organization et al. 2023. Depressive disorder (depression). [find](https://scholar.google.com/scholar?q=World+Health+Organization+et+al%2E+2023%2E+Depressive+disorder+%28depression%29%2E)
31. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
32. Hongzhi Qi, Nan Bai, Jianqiang Li, Wei Zhai, Qing Zhao, Qi Gao, Bing Xiang Yang, and Guanghui Fu. 2025. Generalizable cross-lingual cognitive distortion detection with standardized annotations and multi-task learning. In Findings of the Association for Computational Linguistics: ACL 2025, pages 1604… [find](https://scholar.google.com/scholar?q=Hongzhi+Qi%2C+Nan+Bai%2C+Jianqiang+Li%2C+Wei+Zhai%2C+Qing+Zhao%2C+Qi+Gao%2C+Bing+Xiang+Yang%2C+and+Guanghui+Fu%2E+2025%2E+Generalizable+cross%2Dlingual+cognitive+distortion+detection+with+standardized+annotations+and+mul)
33. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in neural information processing systems, 36:53728–53741.
34. Alexandre Rame, Guillaume Couairon, Corentin Dancette, Jean-Baptiste Gaya, Mustafa Shukor, Laure Soulier, and Matthieu Cord. 2023. [Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards](https://md.research.elamur.ai/free/en/papers/rame-2023-rewarded-soups-towards-pareto-optimal/). Advances in Neural Information Processing Systems, 36:71095–7113…
35. Shyam Sundhar Ramesh, Yifan Hu, Iason Chaimalas, Viraj Mehta, Pier Giuseppe Sessa, Haitham Bou Ammar, and Ilija Bogunovic. 2024. Group robust preference optimization in reward-free rlhf. Advances in Neural Information Processing Systems, 37:37100– 37137. [find](https://scholar.google.com/scholar?q=Shyam+Sundhar+Ramesh%2C+Yifan+Hu%2C+Iason+Chaimalas%2C+Viraj+Mehta%2C+Pier+Giuseppe+Sessa%2C+Haitham+Bou+Ammar%2C+and+Ilija+Bogunovic%2E+2024%2E+Group+robust+preference+optimization+in+reward%2Dfree+rlhf%2E+Advances+in+N)
36. Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2019. Towards empathetic open-domain conversation models: A new benchmark and dataset. In Proceedings of the 57th annual meeting of the association for computational linguistics, pages 5370–5381. [find](https://scholar.google.com/scholar?q=Hannah+Rashkin%2C+Eric+Michael+Smith%2C+Margaret+Li%2C+and+Y%2DLan+Boureau%2E+2019%2E+Towards+empathetic+open%2Ddomain+conversation+models%3A+A+new+benchmark+and+dataset%2E+In+Proceedings+of+the+57th+annual+meeting+of+)
37. Diederik M Roijers, Peter Vamplew, Shimon Whiteson, and Richard Dazeley. 2013. A survey of multi-objective sequential decision-making. Journal of Artificial Intelligence Research, 48:67–113. [find](https://scholar.google.com/scholar?q=Diederik+M+Roijers%2C+Peter+Vamplew%2C+Shimon+Whiteson%2C+and+Richard+Dazeley%2E+2013%2E+A+survey+of+multi%2Dobjective+sequential+decision%2Dmaking%2E+Journal+of+Artificial+Intelligence+Research%2C+48%3A67%E2%80%93113%2E)
38. Ashish Sharma, Kevin Rushton, Inna Lin, David Wadden, Khendra Lucas, Adam Miner, Theresa Nguyen, and Tim Althoff. 2023. Cognitive reframing of negative thoughts through human-language model interaction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volum… [find](https://scholar.google.com/scholar?q=Ashish+Sharma%2C+Kevin+Rushton%2C+Inna+Lin%2C+David+Wadden%2C+Khendra+Lucas%2C+Adam+Miner%2C+Theresa+Nguyen%2C+and+Tim+Althoff%2E+2023%2E+Cognitive+reframing+of+negative+thoughts+through+human%2Dlanguage+model+interactio)
39. Yu Sun, Shuohuan Wang, Shikun Feng, Siyu Ding, Chao Pang, Junyuan Shang, Jiaxiang Liu, Xuyi Chen, Yanbin Zhao, Yuxiang Lu, et al. 2021. [Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation](https://md.research.elamur.ai/free/en/papers/sun-2021-ernie-3-0-large/). arXiv preprint arXiv:2107.02137.
40. Bichen Wang, Pengfei Deng, Yanyan Zhao, and Bing Qin. 2023a. C2d2 dataset: A resource for the cognitive distortion analysis and its impact on mental health. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10149– 10160. [find](https://scholar.google.com/scholar?q=Bichen+Wang%2C+Pengfei+Deng%2C+Yanyan+Zhao%2C+and+Bing+Qin%2E+2023a%2E+C2d2+dataset%3A+A+resource+for+the+cognitive+distortion+analysis+and+its+impact+on+mental+health%2E+In+Findings+of+the+Association+for+Computat)
41. Qing Wang, Shuyuan Peng, Zhiyuan Zha, Xue Han, Chao Deng, Lun Hu, and Pengwei Hu. 2023b. Enhancing the conversational agent with an emotional support system for mental health digital therapeutics. Frontiers in Psychiatry, 14:1148534. [find](https://scholar.google.com/scholar?q=Qing+Wang%2C+Shuyuan+Peng%2C+Zhiyuan+Zha%2C+Xue+Han%2C+Chao+Deng%2C+Lun+Hu%2C+and+Pengwei+Hu%2E+2023b%2E+Enhancing+the+conversational+agent+with+an+emotional+support+system+for+mental+health+digital+therapeutics%2E+Fro)
42. Xiaomeng Wang, Dharmendra Sharma, and Dinesh Kumar. Cognitive reframing via large language models for enhanced linguistic attributes. In The Second Tiny Papers Track at ICLR 2024. [find](https://scholar.google.com/scholar?q=Xiaomeng+Wang%2C+Dharmendra+Sharma%2C+and+Dinesh+Kumar%2E+Cognitive+reframing+via+large+language+models+for+enhanced+linguistic+attributes%2E+In+The+Second+Tiny+Papers+Track+at+ICLR+2024%2E)
43. Wei Zhai, Nan Bai, Qing Zhao, Jianqiang Li, Fan Wang, Hongzhi Qi, Meng Jiang, Xiaoqin Wang, Bing Xiang Yang, and Guanghui Fu. 2025. Mentalglm series: Explainable large language models for mental health analysis on chinese social media. In Proceedings of the 2025 Conference on Empirical Methods in Na… [find](https://scholar.google.com/scholar?q=Wei+Zhai%2C+Nan+Bai%2C+Qing+Zhao%2C+Jianqiang+Li%2C+Fan+Wang%2C+Hongzhi+Qi%2C+Meng+Jiang%2C+Xiaoqin+Wang%2C+Bing+Xiang+Yang%2C+and+Guanghui+Fu%2E+2025%2E+Mentalglm+series%3A+Explainable+large+language+models+for+mental+healt)
44. Wei Zhai, Hongzhi Qi, Qing Zhao, Jianqiang Li, Ziqi Wang, Han Wang, Bing Yang, and Guanghui Fu. 2024. Chinese mentalbert: Domain-adaptive pre-training on social media for chinese mental health text analysis. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10574– 10585. [find](https://scholar.google.com/scholar?q=Wei+Zhai%2C+Hongzhi+Qi%2C+Qing+Zhao%2C+Jianqiang+Li%2C+Ziqi+Wang%2C+Han+Wang%2C+Bing+Yang%2C+and+Guanghui+Fu%2E+2024%2E+Chinese+mentalbert%3A+Domain%2Dadaptive+pre%2Dtraining+on+social+media+for+chinese+mental+health+text+an)
45. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675. [find](https://scholar.google.com/scholar?q=Tianyi+Zhang%2C+Varsha+Kishore%2C+Felix+Wu%2C+Kilian+Q+Weinberger%2C+and+Yoav+Artzi%2E+2019%2E+Bertscore%3A+Evaluating+text+generation+with+bert%2E+arXiv+preprint+arXiv%3A1904%2E09675%2E)
46. Caleb Ziems, Minzhi Li, Anthony Zhang, and Diyi Yang. 2022. Inducing positive perspectives with text reframing. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3682–3700. [find](https://scholar.google.com/scholar?q=Caleb+Ziems%2C+Minzhi+Li%2C+Anthony+Zhang%2C+and+Diyi+Yang%2E+2022%2E+Inducing+positive+perspectives+with+text+reframing%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computational+Linguisti)

*Updated 2 November 2026*