conftrace_

representation steering

9 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (5) model alignment (2) representation learning (2) activation editing (1) spectral projection (1) fairness auditing (1) language model detoxification (1) toxicity reduction (1) llm safety (1) safety mechanism (1)

Papers

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models ACL 2026 SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering ACL 2026 SCoUT: A Framework for Structured Stereotype Analysis in Language Models AAAI 2026 Steering Representations, Safeguarding Privacy: A Cross-Modal Privacy Protection Method for Generative AI AAAI 2026 AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models ACL 2025 Multi-Attribute Steering of Language Models via Targeted Intervention ACL 2025 On Effects of Steering Latent Representation for Large Language Model Unlearning AAAI 2025 Spectral Editing of Activations for Large Language Model Alignment NeurIPS 2024 Self-Detoxifying Language Models via Toxification Reversal EMNLP 2023