Conversations Gone Awry, But Then? Evaluating Conversational Forecasting Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tran, Son Quoc, Gangavarapu, Tushaar, Chernogor, Nicholas, Chang, Jonathan P., Danescu-Niculescu-Mizil, Cristian
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908467603701760
author Tran, Son Quoc
Gangavarapu, Tushaar
Chernogor, Nicholas
Chang, Jonathan P.
Danescu-Niculescu-Mizil, Cristian
author_facet Tran, Son Quoc
Gangavarapu, Tushaar
Chernogor, Nicholas
Chang, Jonathan P.
Danescu-Niculescu-Mizil, Cristian
contents We often rely on our intuition to anticipate the direction of a conversation. Endowing automated systems with similar foresight can enable them to assist human-human interactions. Recent work on developing models with this predictive capacity has focused on the Conversations Gone Awry (CGA) task: forecasting whether an ongoing conversation will derail. In this work, we revisit this task and introduce the first uniform evaluation framework, creating a benchmark that enables direct and reliable comparisons between different architectures. This allows us to present an up-to-date overview of the current progress in CGA models, in light of recent advancements in language modeling. Our framework also introduces a novel metric that captures a model's ability to revise its forecast as the conversation progresses.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19470
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conversations Gone Awry, But Then? Evaluating Conversational Forecasting Models
Tran, Son Quoc
Gangavarapu, Tushaar
Chernogor, Nicholas
Chang, Jonathan P.
Danescu-Niculescu-Mizil, Cristian
Computation and Language
Human-Computer Interaction
We often rely on our intuition to anticipate the direction of a conversation. Endowing automated systems with similar foresight can enable them to assist human-human interactions. Recent work on developing models with this predictive capacity has focused on the Conversations Gone Awry (CGA) task: forecasting whether an ongoing conversation will derail. In this work, we revisit this task and introduce the first uniform evaluation framework, creating a benchmark that enables direct and reliable comparisons between different architectures. This allows us to present an up-to-date overview of the current progress in CGA models, in light of recent advancements in language modeling. Our framework also introduces a novel metric that captures a model's ability to revise its forecast as the conversation progresses.
title Conversations Gone Awry, But Then? Evaluating Conversational Forecasting Models
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2507.19470