Shape it Up! Restoring LLM Safety during Finetuning
- Shengyun Peng
- Pin-Yu Chen
- et al.
- 2025
- NeurIPS 2025
Conference paper
Publications
960 results for Trustworthy AI
CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
- Chen Xiong
- Pin-Yu Chen
- et al.
- 2025
- NeurIPS 2025
Conference paperCausally Reliable Concept Bottleneck Models
- Giovanni De Felice
- Arianna Casanova Flores
- et al.
- 2025
- NeurIPS 2025
Conference paperFoundation Models Enabling Multi-Scale Battery Materials Discovery: From Molecules To Devices
- Vidushi Sharma
- Andy Tek
- et al.
- 2025
- NeurIPS 2025
Workshop paperThe Shepherd Test: How Will Superintelligent Agents Balance Care and Control in Asymmetric Relationships?
- Djallel Bouneffouf
- Matthew Riemer
- et al.
- 2025
- NeurIPS 2025
Workshop 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 paperSpecifying exact circuit algorithms in universal transformers
- Taku Ito
- Ruchir Puri
- et al.
- 2025
- NeurIPS 2025
Workshop paperMEAL: A Multi-dimensional Evaluation of Alignment Techniques for LLMs
- Muneeza Azmat
- Momin Abbas
- et al.
- 2025
- NeurIPS 2025
Workshop paperContextual Bandits for Large-Scale Structured Discrete Constrained Optimization Problems
- Pavithra Harsha
- Chitra Subramanian
- et al.
- 2025
- NeurIPS 2025
Workshop paperDynamic Features Adaptation in Networking: Toward Flexible training and Explainable inference
- 2025
- NeurIPS 2025
Workshop paper