conftrace_

utility

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) trade-off (2) guardrails (1) selective suppression (1) security fine-tuning (1) leakage (1) least-privilege learning (1) delta parameters (1) preferences (1) calibration datasets (1)

Papers

Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models ICML 2025 Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents ICML 2025 Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets ICML 2025 The Jailbreak Tax: How Useful are Your Jailbreak Outputs? ICML 2025 The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning ICLR 2025 Centralized Selection with Preferences in the Presence of Biases ICML 2024 Instruction Tuning for Secure Code Generation ICML 2024 LLMSYN: Generating Synthetic Electronic Health Records Without Patient-Level Data MLHC 2024 MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective ICML 2024 Model Alignment as Prospect Theoretic Optimization ICML 2024 The Fundamental Limits of Least-Privilege Learning ICML 2024