conftrace_

rejection learning

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) vision domain attack (1) malicious data curation (1) classification system (1) phi-divergence regularization (1) confidence tokens (1) error-based feedback (1) routing (1) risk optimization (1) self reflection (1)

Papers

Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models? CVPR 2025 Learning to Route LLMs with Confidence Tokens ICML 2025 Rejection via Learning Density Ratios NeurIPS 2024 Learning with Rejection for Abstractive Text Summarization EMNLP 2022 Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer NeurIPS 2018