A RAG system over U.S. transportation cybersecurity statutes scores higher than vanilla chatbots on the authors' 59-question benchmark, but the benchmark gives the RAG system the source documents and withholds them from the baselines.
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corresponding dataset is scarce. We propose a taxonomy for dialogue safety specifically designed to capture unsafe behaviors in human-bot dialogue settings, with focuses on context-sensitive unsafety, which is under-explored in prior works. To spur research in this direction, we compile DiaSafety, a dataset with rich context-sensitive unsafe examples. Experiments show that existing safety guarding tools fail severely on our dataset. As a remedy, we train a dialogue safety classifier to provide a strong baseline for context-sensitive dialogue unsafety detection. With our classifier, we perform safety evaluations on popular conversational models and show that existing dialogue systems still exhibit concerning context-sensitive safety problems.
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps
A RAG system over U.S. transportation cybersecurity statutes scores higher than vanilla chatbots on the authors' 59-question benchmark, but the benchmark gives the RAG system the source documents and withholds them from the baselines.