conftrace_

refusal behavior

13 papers

Explore in graph

Co-occurring keywords

large language model (13587) safety alignment (178) sparse autoencoder (112) language model (4599) model alignment (226) activation steering (45) user persona (11) ai safety (235) model safety (101) responsible ai (182)

Papers

FinHarmBench: Financial Jailbreak Benchmark and Unsupervised Safety Fine-Tuning via Refusal Steering Distillation ACL 2026
Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models EACL 2026
Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal AAAI 2026
The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs EACL 2026
Understanding Refusal in Language Models with Sparse Autoencoders EMNLP 2025
The Hallucination Tax of Reinforcement Finetuning EMNLP 2025
Path Drift in Large Reasoning Models: How First-Person Commitments Override Safety EMNLP 2025
SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering AAAI 2025
COVER: Context-Driven Over-Refusal Verification in LLMs ACL 2025
Alignment for Honesty NIPS 2024
ChatGPT Doesn’t Trust Chargers Fans: Guardrail Sensitivity in Context EMNLP 2024
Who's asking? User personas and the mechanics of latent misalignment NIPS 2024
Navigating the OverKill in Large Language Models ACL 2024