conftrace_

alignment mechanism

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reinforcement learning (2) unlearnable data (1) disclaimer injection (1) large language model (1) attack success rate (1) math word problem (1) copy mechanism (1) black-box defense (1) sequence-to-sequence model (1) safety fine-tuning (1)

Papers

CAP: Controllable Alignment Prompting for Unlearning in LLMs ACL 2026 Rendering Data Unlearnable by Exploiting LLM Alignment Mechanisms ACL 2026 Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM AAAI 2025 Neural Math Word Problem Solver with Reinforcement Learning COLING 2018