The paper presents the first uniform benchmark for conversation derailment forecasting, a new CGA-CMV-large dataset, and a Forecast Recovery metric, with Gemma2 9B reaching state-of-the-art accuracy.
Chang, Charlotte Schluger, and Cristian Danescu-Niculescu-Mizil
1 Pith paper cite this work, alongside 23 external citations. Polarity classification is still indexing.
1
Pith paper citing it
23
external citations · OpenAlex
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Conversations Gone Awry, But Then? Evaluating Conversational Forecasting Models
The paper presents the first uniform benchmark for conversation derailment forecasting, a new CGA-CMV-large dataset, and a Forecast Recovery metric, with Gemma2 9B reaching state-of-the-art accuracy.