CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
- Chen Xiong
- Pin-Yu Chen
- et al.
- 2025
- NeurIPS 2025
Conference paper
Publications
934 results for Trustworthy AI
Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search
- Yanbo Wang
- Zixiang Xu
- et al.
- 2025
- NeurIPS 2025
Conference paperShape it Up! Restoring LLM Safety during Finetuning
- Shengyun Peng
- Pin-Yu Chen
- et al.
- 2025
- NeurIPS 2025
Conference paperFair Continuous Resource Allocation with Equality of Impact
- Blossom Metevier
- Dennis Wei
- et al.
- 2025
- NeurIPS 2025
Conference paperKnow What You Don't Know: Uncertainty Calibration of Process Reward Models
- Young Jin Park
- Kristjan Greenewald
- et al.
- 2025
- NeurIPS 2025
Conference paperBenchmarkCards: Standardized Documentation for Large Language Model Benchmarks
- Anna Sokol
- Elizabeth Daly
- et al.
- 2025
- NeurIPS 2025
Conference paperFinal-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
- Dennis Wei
- Inkit Padhi
- et al.
- 2025
- NeurIPS 2025
Conference paperCausally Reliable Concept Bottleneck Models
- Giovanni De Felice
- Arianna Casanova Flores
- et al.
- 2025
- NeurIPS 2025
Conference paperToward a Coherent Virtual Cell Model: Probing Biological World-Model Coherence in Transcriptomic Foundation Models
- Noa Moriel
- Yishai Shimoni
- et al.
- 2025
- NeurIPS 2025
Workshop paperQuantifying policy uncertainty in generative flow networks with uncertain rewards
- Ramon Nartallo-kaluarachchi
- Robert Manson Sawko
- et al.
- 2025
- NeurIPS 2025
Workshop paper