NeurIPS 2025 TrustLLM WorkshopSchedule
| Time | Session | Description | Duration(mins) |
|---|---|---|---|
Dec 06, 16:00 | Opening Remark | Opening Remark Wei Huang | 10 |
Dec 06, 16:10 | Invited Talk 1 | TBD Yoshua Bengio | 40 |
Dec 06, 16:50 | Invited Talk 2 | TBD Ahmad Beirami | 40 |
Dec 06, 17:30 | Coffee Break | Poster Session | 50 |
Dec 06, 18:20 | Invited Talk 3 | TBD Furong Huang | 40 |
Dec 06, 19:00 | Oral Presentation | TBD TBD | 30 |
Dec 06, 19:30 | Lunch | Lunch - | 90 |
Dec 06, 21:00 | Invited Talk 4 | TBD Bo Li | 40 |
Dec 06, 21:40 | Invited Talk 5 | TBD Yu Yang | 40 |
Dec 06, 22:20 | Oral Presentation | TBD TBD | 30 |
Dec 06, 22:50 | Invited Talk 6 | TBD Yihe Deng | 40 |
Dec 06, 23:30 | Panel Discussion | From Theory to Deployment: Process-Level Safety in LRMs Panelists: - Junchi Yan (SJTU) - Zhangyang Atlas Wang (XTX Markets & UT Austin) - Atsushi Nitanda (A*STAR & NTU) - Maksym Andriushchenko (EPFL) - Yihe Deng (UCLA) | 40 |
Dec 07, 00:10 | Interactive Breakout | Breakout Session - | 30 |
Invalid Date NaN, NaN:NaN | Closing Remark | Closing Remark Wei Huang | 20 |
Call for Papers
Description
Recent breakthroughs in large reasoning models (LRMs)—systems that perform explicit, multi-step inference at test time—have unlocked impressive gains across science, mathematics, and law (Guo et al., 2025; Snell et al., 2024). Yet these very reasoning chains introduce novel trust risks that scale-only LLM studies overlook: small logic slips can snowball, intermediate states become new attack surfaces, and plausible-but-false proofs can elude standard output-level filters (Geiping et al., 2025).
What sets this workshop apart: Prior workshops focused on generic robustness; This workshop aims to bring together researchers and practitioners to systematically explore, characterize, and address these emergent trust risks in large reasoning models. We seek to move beyond traditional evaluation of final LLM outputs, instead focusing on the full process of reasoning: how errors propagate, how uncertainty compounds, how transparency and accountability are affected, and what new opportunities exist for robust evaluation and intervention (Zhu et al., 2025; Ouyang et al., 2024).
Core Research Questions
- Risk Landscape — Which process-level failure modes threaten high-stakes deployment?
- Metric Design — How can we measure and benchmark step-wise safety at scale?
- Prototype Validation — What lightweight tools or model patches can we release now to seed wider research?
Topics of Interest
- Failure modes and risk propagation in multi-step reasoning
- Adversarial attacks and defenses in inference-time reasoning.
- Evaluation metrics and empirical benchmarks for reasoning safety.
- Uncertainty quantification, error detection, and correction in reasoning processes.
- Approaches for improving interpretability and transparency of reasoning chains.
- Causal analysis as one lens for understanding reasoning failures.
- Human-AI trust, calibration, and collaborative reasoning.
- Case studies of reasoning models in real-world high-stakes domains.
- New architectures or algorithms for safer, more robust reasoning.
Submission Guide
Submission Instructions
We invite submissions of up to 8 pages (excluding references and appendices). The main manuscript and any appendices must be submitted as a single PDF file through the OpenReview portal (the official workshop venue link will be posted on the website). Papers previously published at other conferences will not be considered for acceptance
Each paper receives no less than 3 reviews. Reviewers declare the conflict of interests via the OpenReview interface; organizers will not handle papers with which they have a conflict.
Timelines
| Submissions Deadline | Aug 22th, 2025 |
| Reviewer bidding dates | Aug 22 - 26th, 2025 |
| Review Deadline | Sept 17th, 2025 |
| Paper Notification Date | Sept 22th, 2025 |
| Camera Ready Deadline | Nov 5th, 2025 |
All deadlines are specified in 23:59AoE (Anywhere on Earth).
Program Committee
Zijun Chen (SJTU)
Yi Liu (CityU HK)
Yi Ding (Purdue)
Zhuang Luo (Meta)
Bowei He (CityU HK, MBZUAI)
Zachary Yang (McGill)
Nathan Roll (Stanford)
Weijie Xu (Amazon)
Yihao Zhang (PKU)
Jungang Li (HKUST)
Kejia Chen (ZJU)
Yuechen Jiang (UH Mānoa)
Yang Li (SJTU)
Shaobo Wang (SJTU)
Jianhao Huang (SJTU)
Qibing Ren (SJTU)
Tongcheng Zhang (SJTU)
Xiaoxuan Lei (McGill)
Shan Chen (Harvard)
Xueying Ma (Columbia)
Junqi Jinag (ICL)
Qin Liu (UC Davis)
Weiwei Jiang (BUPT)
Zhexu Liu (RPI)
Hongyi Liu (Amazon)
Lingyun Wang (Pitt)
Yingzhou Lu (Stanford)
Yicheng Fu (Stanford)
Xinhe Xu (UIUC)
Mingyang Wang (LMU)
Andy Su (Meta & Princeton)
Jishen Yang (Amazon)
Simin Fan (EPFL)
Yibo Miao (CAS)
Gyuwan Kim (UCSB)
Shraddha Barke (Microsoft)
Xiangjun Dong (Texas A&M)
Atharva Kulkarni (USC)
Ruixuan Liu (Emory)
Zhexin Zhang (THU)
Caihua Li (Yale)
Yongyi Yang (UMich)
Mao Cheng (Meta)
Huaijin Wu (SJTU)
Lei Yu (Meta)
He Zhang (RMIT)
Saptarshi Saha (ISIK)
Xia Song (NTU)
Fiez Hussein Khleaf KHLEAF (Sakarya)
Ryotaro Kawata (UTokyo)
Rei Higuchi (UTokyo)
Naoki Nishikawa (UTokyo)
Chengyuan Deng (Rutgers)
Fanhu Zeng (CAS)
Zhiwei Xu (UMich)
Binh Nguyen (NUS)
Yunting Yin (EMU)
Jiawei Yan (Roche)
Jiahao Yuan (ECNU)
Shurui Li (Waymo)
Siqi Cao (JHU)
Youngsun Lim (Boston)
Frequently Asked Questions
Can we submit a paper that will also be submitted to NeurIPS 2025?
Yes.
Can we submit a paper that was accepted at ICML 2025?
No. ICML prohibits main conference publication from appearing concurrently at the workshops.
Will the reviews be made available to authors?
Yes.
I have a question not addressed here, whom should I contact?
Email organizers at trustllm-workshop@googlegroups.com
References
[1] Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X. and Zhang, X., 2025. Deepseek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948.
[2] Snell, C., Lee, J., Xu, K. and Kumar, A., 2024. Scaling LLM test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:2408.03314.
[3] Muennighoff, N., Yang, Z., Shi, W., Li, X.L., Fei-Fei, L., Hajishirzi, H., Zettlemoyer, L., Liang, P., Candès, E. and Hashimoto, T., 2025. s1: Simple test-time scaling. arXiv preprint arXiv:2501.19393.
[4] Geiping, J., McLeish, S., Jain, N., Kirchenbauer, J., Singh, S., Bartoldson, B.R., Kailkhura, B., Bhatele, A. and Goldstein, T., 2025. Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach. arXiv preprint arXiv:2502.05171.
[5] Zhu, J., Yan, L., Wang, S., Yin, D. and Sha, L., 2025. Reasoning-to-defend: Safety-aware reasoning can defend large language models from Jailbreaking. arXiv preprint arXiv:2502.12970.