SpeakSoftly: Scaffolding Nonviolent Communication in Intimate Relationships through LLM-Powered Just-In-Time Interventions

2026-04-06

AI Summary

This study addresses the challenge of verbal aggression in intimate relationships stemming from miscommunication in text-based interactions, highlighting the urgent need for timely and effective nonviolent communication (NVC) support. The work proposes the first integration of the NVC framework with large language models (LLMs), introducing two core functionalities—NVC-Prompt and NVC-Guide—and designing three progressive intervention modes that enable context-aware, dynamic guidance to help users recognize their own and their partner’s emotions and underlying needs. Experimental results from both simulated and real conflict scenarios demonstrate that the Empathetic Guide significantly fosters cognitive and behavioral change, whereas the Neutral Guide proves more effective in actual conflicts due to its lower cognitive load, underscoring the critical importance of aligning intervention depth with situational context.

Abstract

Conflicts are common in text-based communication, particularly in intimate relationships, where misunderstandings can easily escalate into verbal aggression. To address this, we present SpeakSoftly, a system that applies Nonviolent Communication (NVC) principles to scaffold couples' conflict communication through LLM-powered just-in-time interventions. Informed by formative interviews with couples and NVC principles, we designed two core features: NVC-Prompt, which detects verbal aggression and suggests revisions to prevent escalation, and NVC-Guide, which analyzes dialogues to uncover users' feelings and needs, fostering self-awareness and perspective-taking. These features were implemented across three progressive intervention modes, each varying in intervention depth and tone: Basic Reminder, Neutral Guide, and Empathetic Guide. We conducted a mixed-methods user study with 18 couples across simulated and real-life conflict settings to evaluate the effectiveness of each mode. Results showed that Empathetic Guide significantly facilitated both behavioral and cognitive changes, while Neutral Guide was effective only for behavioral changes in simulated conflicts. In real-life conflicts, Neutral Guide showed distinct advantages due to lower cognitive load demands. We discuss the mechanisms behind these findings and propose design implications for in-situ interventions in high-stakes communication contexts.

Problem

• Nonviolent Communication
• Intimate Relationships
• Verbal Aggression
• Just-in-Time Intervention
• Conflict Communication

Innovation

• Nonviolent Communication
• LLM-powered intervention
• just-in-time scaffolding
• conflict de-escalation
• empathetic AI