conftrace_

language model safety

16 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (5) ai safety (4) red teaming (3) jailbreak attack (3) safety evaluation (3) language model (3) adversarial attack (3) responsible ai (3) safety vulnerability (2) llm safety (2)

Papers

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin AAAI 2026 BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage EACL 2026 Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models ACL 2026 A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs EMNLP 2025 Backtracking Improves Generation Safety ICLR 2025 h4rm3l: A Language for Composable Jailbreak Attack Synthesis ICLR 2025 How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis EMNLP 2025 LongSafety: Evaluating Long-Context Safety of Large Language Models ACL 2025 PL-Guard: Benchmarking Language Model Safety for Polish ACL 2025 SAFENUDGE: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs EMNLP 2025 ChatGPT Doesn’t Trust Chargers Fans: Guardrail Sensitivity in Context EMNLP 2024 CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference EMNLP 2024 Detoxifying Large Language Models via Knowledge Editing ACL 2024 SocialStigmaQA: A Benchmark to Uncover Stigma Amplification in Generative Language Models AAAI 2024 STAR: SocioTechnical Approach to Red Teaming Language Models EMNLP 2024 SafeText: A Benchmark for Exploring Physical Safety in Language Models EMNLP 2022