Papers Dialogue Safety Prediction

“Dialogue Safety Prediction” 태그가 달린 논문 3편 · 필터 해제

Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations

2024-04-15 · David Nadeau, Mike Kroutikov, Karen McNeil, Simon Baribeau

This paper introduces fourteen novel datasets for the evaluation of Large Language Models' safety in the context of enterprise tasks. A method was devised to evaluate a model's safety, as determined by its ability to fol…

Benchmarking Bias Detection Dialogue Safety Prediction Hallucination

ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming

2024-04-06 · Simone Tedeschi, Felix Friedrich, Patrick Schramowski, Kristian Kersting 외

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical beha…

Adversarial Robustness Dialogue Safety Prediction Red Teaming

ProsocialDialog: A Prosocial Backbone for Conversational Agents

2022-05-25 · Hyunwoo Kim, Youngjae Yu, Liwei Jiang, Ximing Lu 외

Most existing dialogue systems fail to respond properly to potentially unsafe user utterances by either ignoring or passively agreeing with them. To address this issue, we introduce ProsocialDialog, the first large-scale…

Dialogue Generation Dialogue Safety Prediction Response Generation Rules-of-thumb Generation