ProbeLLM: Automating Principled Diagnosis of LLM Failures
- Yue Huang
- Zhengzhe Jiang
- et al.
- 2026
- ICML 2026
Conference paper
Publications
943 results for Trustworthy AI
Position: Agentic Systems Should be General
- Elron Bandel
- Asaf Yehudai
- et al.
- 2026
- ICML 2026
Conference paperThe Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
- Rongzhe Wei
- Peizhi Niu
- et al.
- 2026
- ICML 2026
Conference paperCGU-Bayes: Causal Graph Uncertainty-Guided Bayesian Inference for Domain Generalization
- Naiyu Yin
- Hanjing Wang
- et al.
- 2026
- CVPR 2026
Conference paperUnsupervised Cycle Detection in Agentic Applications
- Felix George
- Divya Pathak
- et al.
- 2026
- ICPE 2026
Short paperDropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
- Jenny Huang
- Yunyi Shen
- et al.
- 2026
- ICLR 2026
Conference paperAdaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring
- Natalia Martinez Gil
- Fearghal O'Donncha
- et al.
- 2026
- ICLR 2026
Conference paperWhen Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
- Aladin Djuhera
- Farhan Ahmed
- et al.
- 2026
- ICLR 2026
Conference paperBranch and Bound Search for Exact MAP Inference in Credal Networks
- Radu Marinescu
- Fabio Cozman
- et al.
- 2026
- ICLR 2026
Conference paperDetective SAM: Adaptive AI-Image Forgery Localization
- Gert Lek
- Nicolas Van Schaik
- et al.
- 2026
- ICLR 2026
Conference paper