conftrace_

over refusal

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) deliberative alignment (1) case augmented reasoning (1) safety reasoning chain (1) benchmark (1) safety (1) rejection categories (1) toxic prompts (1) advanced teacher model (1) overgeneration (1)

Papers

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety ACL 2026 Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning ICML 2025 OR-Bench: An Over-Refusal Benchmark for Large Language Models ICML 2025 POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization ICML 2025