conftrace_

conversational safety

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

dialogue system (2) feedback handling (1) safety failure (1) unsafe behavior (1) response rewriting (1) annotation alignment (1) large language model (1) demographic disparity (1) toxic language detection (1) open-domain conversation (1)

Papers

Annotation alignment: Comparing LLM and human annotations of conversational safety EMNLP 2024 SafeConv: Explaining and Correcting Conversational Unsafe Behavior ACL 2023 SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures ACL 2022