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

• URL: http://arxiv.org/abs/2505.21451v1
• Date: Tue, 27 May 2025 17:23:57 GMT
• Title: Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication
• Authors: Jocelyn Shen, Akhila Yerukola, Xuhui Zhou, Cynthia Breazeal, Maarten Sap, Hae Won Park,
• Abstract summary: We leverage nonviolent communication (NVC) theory to evaluate LLMs in detecting conversational breakdowns.<n>We find that the polarity of relationship backstories significantly shifted human perception of communication breakdowns.<n>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.
• Score: 33.66989794769884
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Aligning Spoken Dialogue Models from User Interactions [55.192134724622235]
  We propose a novel preference alignment framework to improve spoken dialogue models on realtime conversations from user interactions.<n>We create a dataset of more than 150,000 preference pairs from raw multi-turn speech conversations annotated with AI feedback.<n>Our findings shed light on the importance of a well-calibrated balance among various dynamics, crucial for natural real-time speech dialogue systems.
  arXiv  Detail & Related papers  (2025-06-26T16:45:20Z)
• When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation [18.650805984660707]
  Endowing dialogue agents with persona information has proven to significantly improve the consistency and diversity of their generations.<n>While much focus has been placed on aligning dialogues with provided personas, the adaptation to the interlocutor's profile remains largely underexplored.<n>We investigate three key aspects: (1) a model's ability to align responses with both the provided persona and the interlocutor's; (2) its robustness when dealing with familiar versus unfamiliar interlocutors and topics, and (3) the impact of additional fine-tuning on specific persona-based dialogues.
  arXiv  Detail & Related papers  (2025-05-30T14:04:30Z)
• Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance [73.19687314438133]
  We study how reliance is affected by contextual features of an interaction. We find that contextual characteristics significantly affect human reliance behavior. Our results show that calibration and language quality alone are insufficient in evaluating the risks of human-LM interactions.
  arXiv  Detail & Related papers  (2024-07-10T18:00:05Z)
• GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment [72.96949760114575]
  We propose a novel cooperative communication framework, Goal-Oriented Mental Alignment (GOMA)<n>GOMA formulates verbal communication as a planning problem that minimizes the misalignment between parts of agents' mental states that are relevant to the goals.<n>We evaluate our approach against strong baselines in two challenging environments, Overcooked (a multiplayer game) and VirtualHome (a household simulator)
  arXiv  Detail & Related papers  (2024-03-17T03:52:52Z)
• Assessing the Impact of Personality on Affective States from Video Game Communication [17.01727448431269]
  Individual differences in personality determine our preferences, traits and values, which should similarly hold for the way we express ourselves. In this exploratory work, we investigate the impact of personality on the tendency how players of a team-based collaborative alternate reality game express themselves affectively.
  arXiv  Detail & Related papers  (2023-09-22T23:24:37Z)
• Affect Recognition in Conversations Using Large Language Models [9.689990547610664]
  Affect recognition plays a pivotal role in human communication. This study investigates the capacity of large language models (LLMs) to recognise human affect in conversations.
  arXiv  Detail & Related papers  (2023-09-22T14:11:23Z)
• The More Similar, the Better? Associations between Latent Semantic Similarity and Emotional Experiences Differ across Conversation Contexts [39.58317527488534]
  Latent semantic similarity (LSS) is a measure of the similarity of information exchanges in a conversation.<n>This work highlights the importance of context in understanding the emotional correlates of LSS.
  arXiv  Detail & Related papers  (2023-09-22T06:37:45Z)
• HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer [38.92436852096451]
  Cross-person memory Transformer (CPM-T) framework is able to explicitly model affective dynamics. CPM-T framework maintains memory modules to store and update the contexts within the conversation window. We evaluate the effectiveness and generalizability of our approach on three publicly available datasets for joint engagement, rapport, and human beliefs prediction tasks.
  arXiv  Detail & Related papers  (2023-05-21T06:43:35Z)
• BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios [14.23697277904244]
  This paper uses the combined knowledge of Theory of Mind (ToM) and Object-Context Relations to investigate methods for enhancing collaboration between humans and autonomous systems. We propose a novel and challenging multimodal video dataset for assessing the capability of artificial intelligence (AI) systems in predicting human belief states in an object-context scenario.
  arXiv  Detail & Related papers  (2022-06-21T18:29:17Z)
• Few-shot Language Coordination by Modeling Theory of Mind [95.54446989205117]
  We study the task of few-shot $textitlanguage coordination$. We require the lead agent to coordinate with a $textitpopulation$ of agents with different linguistic abilities. This requires the ability to model the partner's beliefs, a vital component of human communication.
  arXiv  Detail & Related papers  (2021-07-12T19:26:11Z)
• Is this Dialogue Coherent? Learning from Dialogue Acts and Entities [82.44143808977209]
  We create the Switchboard Coherence (SWBD-Coh) corpus, a dataset of human-human spoken dialogues annotated with turn coherence ratings. Our statistical analysis of the corpus indicates how turn coherence perception is affected by patterns of distribution of entities. We find that models combining both DA and entity information yield the best performances both for response selection and turn coherence rating.
  arXiv  Detail & Related papers  (2020-06-17T21:02:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.