← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Hermit Kingdom Through the Lens of Multiple Perspectives: A Case Study of LLM Hallucination on North Korea COLING 2025
Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025
CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation COLING 2025
Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models COLING 2025
What’s the most important value? INVP: INvestigating the Value Priorities of LLMs through Decision-making in Social Scenarios COLING 2025
PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks EMNLP 2025
MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique EMNLP 2025
HAF-RM: A Hybrid Alignment Framework for Reward Model Training ACL 2025
Towards Statistical Factuality Guarantee for Large Vision-Language Models EMNLP 2025
FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain EMNLP 2025
CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs EMNLP 2025
SConU: Selective Conformal Uncertainty in Large Language Models ACL 2025
SafeScientist: Enhancing AI Scientist Safety for Risk-Aware Scientific Discovery EMNLP 2025
Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens EMNLP 2025
Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience EMNLP 2025
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters NAACL 2025
Decoding Hate: Exploring Language Models’ Reactions to Hate Speech NAACL 2025
SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs NAACL 2025
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring NAACL 2025
From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection NAACL 2025
Have LLMs Reopened the Pandora’s Box of AI-Generated Fake News? NAACL 2025
Extracting and Understanding the Superficial Knowledge in Alignment NAACL 2025
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems ACL 2025
Dynamic Evaluation with Cognitive Reasoning for Multi-turn Safety of Large Language Models ACL 2025
HalLoc: Token-level Localization of Hallucinations for Vision Language Models CVPR 2025