Publications

881 results for Trustworthy AI

Comparison of simulated and observed methane plumes at oil and gas sites in the Permian Basin using advanced dispersion, coupled mesoscale-LES atmospheric modeling, and scientific machine learning
- - Arash Fathi
  - Joao Lucas de Sousa Almeida
  - et al.
- 2025
- AGU 2025
APILOT: Improving the Security and Usability of LLM Code Suggestions via Outdated API Mitigation
- - Weiheng Bai
  - Keyang Xuan
  - et al.
- 2025
- ACSAC 2025
Learn more about our Trustworthy AI work
Cross-Process Defect Attribution using Potential Loss Analysis
- - Ide-San Ide
  - Kohei Miyaguchi
- 2025
- WSC 2025
Adaptive Distraction: Probing LLM Contextual Robustness with Automated Tree Search
- - Yanbo Wang
  - Zixiang Xu
  - et al.
- 2025
- NeurIPS 2025
Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts
- - Andrea Pugnana
  - Riccardo Massidda
  - et al.
- 2025
- NeurIPS 2025
Think Smarter, Not Harder: Uncertainty Calibration of Process Reward Models
- - Young Jin Park
  - Kristjan Greenewald
  - et al.
- 2025
- NeurIPS 2025
CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
- - Chen Xiong
  - Pin-Yu Chen
  - et al.
- 2025
- NeurIPS 2025
Shape it Up! Restoring LLM Safety during Finetuning
- - Shengyun Peng
  - Pin-Yu Chen
  - et al.
- 2025
- NeurIPS 2025
Causally Reliable Concept Bottleneck Models
- - Giovanni De Felice
  - Arianna Casanova Flores
  - et al.
- 2025
- NeurIPS 2025
BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks
- - Anna Sokol
  - Elizabeth Daly
  - et al.
- 2025
- NeurIPS 2025