# Conversations Gone Awry, But Then? Evaluating Conversational Forecasting Models

arXiv: https://arxiv.org/abs/2507.19470 · HTML: https://mlsanity.com/paper/2507.19470/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [Reducing Gender Bias in Abusive Language Detection](https://mlsanity.com/paper/1808.07231/) (2018)
- [Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions](https://mlsanity.com/paper/1602.01103/) (2016)
- [Fairness risk measures](https://mlsanity.com/paper/1901.08665/) (2019)
- [Conversations Gone Awry: Detecting Early Signs of Conversational Failure](https://mlsanity.com/paper/1805.05345/) (2018)
- [ConvoKit: A Toolkit for the Analysis of Conversations](https://mlsanity.com/paper/2005.04246/) (2020)
- [A Just and Comprehensive Strategy for Using NLP to Address Online Abuse](https://mlsanity.com/paper/1906.01738/) (2019)
- [Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective](https://mlsanity.com/paper/2012.12305/) (2020)
- [Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop](https://mlsanity.com/paper/1909.01362/) (2019)
- [Something's Brewing! Early Prediction of Controversy-causing Posts from Discussion Features](https://mlsanity.com/paper/1904.07372/) (2019)
- [Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversations](https://mlsanity.com/paper/2102.08368/) (2021)
- [Conversational Markers of Constructive Discussions](https://mlsanity.com/paper/1604.07407/) (2016)
- [WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community](https://mlsanity.com/paper/1810.13181/) (2018)
- [Dynamic Forecasting of Conversation Derailment](https://mlsanity.com/paper/2110.05111/) (2021)
- [Proactive Moderation of Online Discussions: Existing Practices and the Potential for Algorithmic Support](https://mlsanity.com/paper/2211.16525/) (2022)
- [Thread With Caution: Proactively Helping Users Assess and Deescalate Tension in Their Online Discussions](https://mlsanity.com/paper/2212.01401/) (2022)
- [Trajectories of Blocked Community Members: Redemption, Recidivism and Departure](https://mlsanity.com/paper/1902.08628/) (2019)

## Built on by (most cited first, 2 of 2)

- [Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment](https://mlsanity.com/paper/2605.29243/) (2026)
- [Leveraging Speech Acts for Low-Data and Cross-Domain Conversation Derailment Forecasting](https://mlsanity.com/paper/2608.25359/) (2026)

## Abstract (arXiv)

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.