← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Towards Trustworthy Summarization of Cardiovascular Articles: A Factuality-and-Uncertainty-Aware Biomedical LLM Approach EMNLP 2025
Human-AI Moral Judgment Congruence on Real-World Scenarios: A Cross-Lingual Analysis EMNLP 2025
MULBERE: Multilingual Jailbreak Robustness Using Targeted Latent Adversarial Training EMNLP 2025
Investigating Motivated Inference in Large Language Models EMNLP 2025
Large Language Models as Detectors or Instigators of Hate Speech in Low-resource Ethiopian Languages EMNLP 2025
No for Some, Yes for Others: Persona Prompts and Other Sources of False Refusal in Language Models EMNLP 2025
FLUE: Streamlined Uncertainty Estimation for Large Language Models AAAI 2025
AIA: Autoregression-Based Injection Attacks Against Text2SQL Models AAAI 2025
Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage AAAI 2025
SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering AAAI 2025
Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks AAAI 2025
Attributive Reasoning for Hallucination Diagnosis of Large Language Models AAAI 2025
Security Attacks on LLM-based Code Completion Tools AAAI 2025
SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models AAAI 2025
Multi-Turn Jailbreaking Large Language Models via Attention Shifting AAAI 2025
Investigating the Security Threat Arising from “Yes-No” Implicit Bias in Large Language Models AAAI 2025
FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts AAAI 2025
Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models AAAI 2025
Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers AAAI 2025
Tuning-Free Accountable Intervention for LLM Deployment – a Metacognitive Approach AAAI 2025
Decoupling Metacognition from Cognition: A Framework for Quantifying Metacognitive Ability in LLMs AAAI 2025
STLC-KG:A Social Text Steganalysis Method Combining Large-Scale Language Models and Common-Sense Knowledge Graphs AAAI 2025
Mitigating Social Bias in Large Language Models: A Multi-Objective Approach Within a Multi-Agent Framework AAAI 2025
NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning AAAI 2025
Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset NAACL 2025