Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations

大模型 分类

2025

10-29

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations

10-29

Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment

10-28

Safety Alignment Should Be Made More Than Just a Few Tokens Deep

10-21

Structgpt: A general framework for large language model to reason over structured data

10-18

GRAPHEVAL: A LIGHTWEIGHT GRAPH-BASED LLM FRAMEWORK FOR IDEA EVALUATION

10-16

Making Large Language Models Perform Better in Knowledge Graph Completion

10-16

Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning

10-15

CoLoTa: A Dataset for Entity-based Commonsense Reasoning over Long-Tail Knowledge

10-15

Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models

10-15

GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation