ICLR 2025 Workshop
Building Trust in LLMs and LLM Applications:
From Guardrails to Explainability to Regulation

HOME SPEAKERS AND PANELISTS CALL FOR PAPERS WORKSHOP SCHEDULE

Oral Presentations 1 (2:10pm-2:50pm)

Paper 12

Mind the Gap: A Practical Attack on GGUF Quantization

Paper 31

On-Premises LLM Deployment Demands a Middle Path: Preserving Privacy Without Sacrificing Model

Paper 38

In-Context Meta Learning Induces Multi-Phase Circuit Emergence

Paper 87

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs

ICLR 2025 Workshop - Building Trust in LLMs and LLM Applications: From Guardrails to Explainability to Regulation