Concepedia

SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures

Megan Ung, Jing Xu, Y-Lan Boureau

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2022 · 23 citations · 23 references

Open access

Concepts

ComputingComputer ScienceInterpersonal CommunicationNatural Language ProcessingSafety EngineeringConversation AnalysisConversational InterfacesConversational User InterfacesDialogue SystemsLanguage ModelingSafety CommunicationConversational AgentsDialog SystemsDialogue Response GenerationDialogue-based FeedbackEnd-to-end Dialogue SystemsFeedbackHuman ConversationUser Feedback

Abstract

Warning: this paper contains example data that may be offensive or upsetting.

References

23

Biased assimilation and attitude polarization: The effects of prior theories on subsequently considered evidence.

Charles G. Lord, Lee Ross, Mark R. Lepper · Journal of Personality and Social Psychology · 1979 · 4.4K citations

Social Sciences, Psychology, Social Psychology +14

On the Opportunities and Risks of Foundation Models

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli et al. · arXiv (Cornell University) · 2021 · 2.2K citations · Full text

Computing, Computer Science, Data Science +17

Reliability in Content Analysis.

Klaus Krippendorff · Human Communication Research · 2004 · 2.1K citations

Social Sciences, Psychology, Item Response Theory +11

A Survey on Hate Speech Detection using Natural Language Processing

Anna Grau Schmidt, Michael Wiegand · 2017 · 1.4K citations · Full text

Computing, Computer Science, Computational Linguistics +8

DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation

Yizhe Zhang, Siqi Sun, Michel Galley et al. · 2020 · 1.1K citations · Full text

Computing, Computer Science, Linguistics +12