xinykou

FFT

Benchmark for LLM Harmlessness Evaluation with Factuality, Fairness and Toxicity

assessing_safety_realign

edit_knwoledge

Scenarios-aware Commonsense Correcton via Instance-level Knowledge Injection

FGDILP

Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models (accepted by Nurocomputing)

safety_realignment

A safety realignment framework via subspace-oriented model fusion for large language models (accepted by KBS)

xinykou/safety_realignment

A safety realignment framework via subspace-oriented model fusion for large language models (accepted by KBS)

xinykou/assessing_safety_realign

xinykou/edit_knwoledge

Scenarios-aware Commonsense Correcton via Instance-level Knowledge Injection

xinykou/FGDILP

Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models (accepted by Nurocomputing)