conftrace_

robustness against attack

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

token partitioning (1) dynamic bia (1) deliberative alignment (1) case augmented reasoning (1) safety reasoning chain (1) over refusal (1) llm watermarking (1) semantic fidelity (1)

Papers

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety ACL 2026 Watermarking with Low-Entropy POS-Guided Token Partitioning and Z-Score-Driven Dynamic Bias for Large Language Models EMNLP 2025