SafeGenAi @ NeurIPS 2024
142 papers
Top Research Directions
Research directions most represented by SafeGenAi @ NeurIPS 2024 papers.
Top Authors
Impactful Papers
Papers from SafeGenAi @ NeurIPS 2024 that shaped research clusters.
Foundational
Mitigating Hallucinations in LVLMs via Summary-Guided Decoding
foundational
The Length Hallucination Tradeoff in Vis
Applying Refusal-Vector Ablation to Llama 3.1 70B Agents
foundational
The Safety Alignment Gap in Autonomous A
The effect of fine-tuning on language model toxicity
foundational
Safety Degradation in Fine-Tuned Large L
GuardFormer: Guardrail Instruction Pretraining for Efficient SafeGuarding
foundational
Dynamic Safety Policy Enforcement for La
Preserving Safety in Fine-Tuned Large Language Models: A Systematic Evaluation and Mitigation Strate
foundational
Safety Degradation in Fine-Tuned Large L
Simulation System Towards Solving Societal-Scale Manipulation
foundational
Large Language Models for Agent-Based So
Influential
Mix Data or Merge Models? Optimizing for Performance and Safety in Multilingual Contexts
influential
Merging Specialized Models in Weight Spa
Efficient and Effective Uncertainty Quantification for LLMs
influential
Factual Inaccuracy and Hallucination in
Detecting Origin Attribution for Text-to-Image Diffusion Models in RGB and Beyond
influential
Representing Visual Style through Statis
Large Language Model Benchmarks Do Not Test Reliability
influential
The Annotation Noise Ceiling in Machine
Unlearning in- vs. out-of-distribution data in LLMs under gradient-based methods
influential
Machine Unlearning for Regulatory Data D
MULTIVERSE: Exposing Large Language Model Alignment Problems in Diverse Worlds
influential
Semantic Camouflage for Bypassing Langua
INVESTIGATING ANNOTATOR BIAS IN LARGE LANGUAGE MODELS FOR HATE SPEECH DETECTION
influential
The Mechanics of Bias Amplification in L
Language Models Can Articulate Their Implicit Goals
influential
The Mechanics of Backdoor Attacks in Neu