# Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication

arXiv: https://arxiv.org/abs/2505.21451 · HTML: https://mlsanity.com/paper/2505.21451/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 58 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 17 of 17)

- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Large language models that replace human participants can harmfully misportray and flatten identity groups](https://mlsanity.com/paper/2402.01908/) (2024)
- [Conversations Gone Awry: Detecting Early Signs of Conversational Failure](https://mlsanity.com/paper/1805.05345/) (2018)
- [Virtual Personas for Language Models via an Anthology of Backstories](https://mlsanity.com/paper/2407.06576/) (2024)
- [COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements](https://mlsanity.com/paper/2306.01985/) (2023)
- [Conversations Gone Alright: Quantifying and Predicting Prosocial Outcomes in Online Conversations](https://mlsanity.com/paper/2102.08368/) (2021)
- [EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction](https://mlsanity.com/paper/2102.00272/) (2021)
- [HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs](https://mlsanity.com/paper/2405.17633/) (2024)
- [Modeling Empathic Similarity in Personal Narratives](https://mlsanity.com/paper/2305.14246/) (2023)
- [SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation](https://mlsanity.com/paper/2504.16122/) (2025)
- [LLM-Mirror: A Generated-Persona Approach for Survey Pre-Testing](https://mlsanity.com/paper/2412.03162/) (2024)
- [Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting](https://mlsanity.com/paper/2305.14755/) (2023)
- [Language Models Predict Empathy Gaps Between Social In-groups and Out-groups](https://mlsanity.com/paper/2503.01030/) (2025)
- [Promoting Constructive Deliberation: Reframing for Receptiveness](https://mlsanity.com/paper/2405.15067/) (2024)

## Built on by (most cited first, 4 of 4)

- [Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations](https://mlsanity.com/paper/2604.27093/) (2026)
- [The Hidden Puppet Master: Predicting Human Belief Change in Manipulative LLM Dialogues](https://mlsanity.com/paper/2603.20907/) (2026)
- [Synthia: Scalable Grounded Persona Generation from Social Media Data](https://mlsanity.com/paper/2507.14922/) (2025)
- [Reducing Conversational Escalation in Large Language Model Dialogue with Nonviolent Communication Constraints](https://mlsanity.com/paper/2606.26106/) (2026)

## Abstract (arXiv)

Conversational breakdowns in close relationships are deeply shaped by personal histories and emotional context, yet most NLP research treats conflict detection as a general task, overlooking the relational dynamics that influence how messages are perceived. In this work, we leverage nonviolent communication (NVC) theory to evaluate LLMs in detecting conversational breakdowns and assessing how relationship backstory influences both human and model perception of conflicts. Given the sensitivity and scarcity of real-world datasets featuring conflict between familiar social partners with rich personal backstories, we contribute the PersonaConflicts Corpus, a dataset of N=5,772 naturalistic simulated dialogues spanning diverse conflict scenarios between friends, family members, and romantic partners. Through a controlled human study, we annotate a subset of dialogues and obtain fine-grained labels of communication breakdown types on individual turns, and assess the impact of backstory on human and model perception of conflict in conversation. We find that the polarity of relationship backstories significantly shifted human perception of communication breakdowns and impressions of the social partners, yet models struggle to meaningfully leverage those backstories in the detection task. Additionally, we find that models consistently overestimate how positively a message will make a listener feel. Our findings underscore the critical role of personalization to relationship contexts in enabling LLMs to serve as effective mediators in human communication for authentic connection.