← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language Models ACL 2025
Jailbreak Attack Initializations as Extractors of Compliance Directions EMNLP 2025
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities ACL 2025
CLARITY: Clinical Assistant for Routing, Inference, and Triage EMNLP 2025
Understanding the Dark Side of LLMs’ Intrinsic Self-Correction ACL 2025
Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment EMNLP 2025
Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation ACL 2025
Scalable Surrogate Verification of Image-Based Neural Network Control Systems Using Composition and Unrolling AAAI 2025
Contrasting Adversarial Perturbations: The Space of Harmless Perturbations AAAI 2025
GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization AAAI 2025
LongSafety: Enhance Safety for Long-Context LLMs ACL 2025
Can LLMs Ground when they (Don’t) Know: A Study on Direct and Loaded Political Questions ACL 2025
Using Humor to Bypass Safety Guardrails in Large Language Models ACL 2025
RedHit: Adaptive Red-Teaming of Large Language Models via Search, Reasoning, and Preference Optimization ACL 2025
HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States ACL 2025
CRAFT: Class Ranking Aware Fine-Tuning for Enhanced Out-of-Distribution Detection WACV 2025
The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models COLING 2025
UTF: Under-trained Tokens as Fingerprints —— a Novel Approach to LLM Identification ACL 2025
Superfluous Instruction: Vulnerabilities Stemming from Task-Specific Superficial Expressions in Instruction Templates ACL 2025
Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models ACL 2025
Can LLMs Recognize Their Own Analogical Hallucinations? Evaluating Uncertainty Estimation for Analogical Reasoning ACL 2025
Teaching Large Language Models to Express Knowledge Boundary from Their Own Signals ACL 2025
Jailbreaking? One Step Is Enough! ACL 2025
Pretend Benign: A Stealthy Adversarial Attack by Exploiting Vulnerabilities in Cooperative Perception ICCV 2025
ELAB: Extensive LLM Alignment Benchmark in Persian Language ACL 2025