Reducing Conversational Escalation in Large Language Model Dialogue with Nonviolent Communication Constraints

• URL: http://arxiv.org/abs/2606.26106v1
• Date: Fri, 01 May 2026 16:22:46 GMT
• Title: Reducing Conversational Escalation in Large Language Model Dialogue with Nonviolent Communication Constraints
• Abstract summary: Large language models (LLMs) are increasingly used in emotionally charged situations involving interpersonal conflict, frustration, and distress.<n>We investigate whether LLMs can be guided toward more de-escalating dialogue behavior through lightweight prompt-level constraints derived from Nonviolent Communication (NVC)<n>We show that NVC-constrained prompting consistently reduces conversational escalation and stabilizes interactions with highly resistant users.
• Score: 3.141210160384506
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly used in emotionally charged situations involving interpersonal conflict, frustration, and distress. While prior safety research has focused on preventing explicit harms such as toxic or policy-violating content, less attention has been paid to conversational behaviors that may unintentionally escalate conflict. In this paper, we investigate whether LLMs can be guided toward more de-escalating dialogue behavior through lightweight prompt-level constraints derived from Nonviolent Communication (NVC). We reformulate NVC principles as process-oriented guidelines that discourage blame attribution, emphasize attention to users' emotional experiences, and encourage clarification before advice. Using a dual-agent simulation framework across multiple instruction-tuned models and user resistance levels, we show that NVC-constrained prompting consistently reduces conversational escalation and stabilizes interactions with highly resistant users. These results suggest that simple communication constraints can meaningfully improve the trustworthiness of LLM dialogue in conflict-prone settings.

Related papers

• Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions [52.45054413627452]
  TPI-Train is a dataset of 88K instances designed with speaker-aware hard negatives to enforce acoustic cue prioritization for interruption handling.<n>TPI-Bench is a comprehensive evaluation framework designed to rigorously measure the interruption-handling strategy.
  arXiv  Detail & Related papers  (2026-04-19T10:03:42Z)
• When Contextual Inference Fails: Cancelability in Interactive Instruction Following [51.2195840589474]
  We introduce Build What I Mean, an interactive benchmark for contextual meaning construction.<n>In BWIM, models must resolve ambiguity by either performing a contextual inference or requesting clarification at a small communication cost.<n>We observe suboptimal strategies, such as partner-blind over-clarification and question-averse guessing under uncertainty.
  arXiv  Detail & Related papers  (2026-03-20T14:46:59Z)
• Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation [26.91734024759386]
  We argue that the root cause lies in an intent alignment gap rather than intrinsic capability deficits.<n>We propose to decouple intent understanding from task execution through a Mediator-Assistant architecture.
  arXiv  Detail & Related papers  (2026-02-07T03:41:04Z)
• ICPO: Illocution-Calibrated Policy Optimization for Multi-Turn Conversation [21.69212076688903]
  Large Language Models (LLMs) in multi-turn conversations often suffer from a lost-in-conversation'' phenomenon.<n>We find that standard post-training techniques like Reinforcement Learning with Verifiable Rewards (RLVR) exacerbate this issue.<n>We propose Illocution-Calibrated Policy Optimization (ICPO), a novel training framework that sensitizes the model to instruction ambiguity.
  arXiv  Detail & Related papers  (2026-01-20T04:39:28Z)
• ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue [16.32928730900186]
  Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue.<n>Existing approaches primarily focus on extending the context window, introducing external memory, or applying context compression.<n>We propose the textbfAdaptive textbfContext textbfRefactoring textbf(ACR) Framework, which dynamically monitors and reshapes the interaction history to contextual inertia and state drift actively.
  arXiv  Detail & Related papers  (2026-01-09T07:17:28Z)
• Context-aware Fairness Evaluation and Mitigation in LLMs [16.594400974742523]
  Large language models often display undesirable behaviors embedded in their internal representations.<n>Pruning-based methods provide a flexible and transparent way to reduce bias by adjusting the neurons responsible for certain behaviors.<n>We propose a dynamic, reversible, pruning-based framework that detects context-aware neuron activations and applies adaptive masking to modulate their influence during generation.
  arXiv  Detail & Related papers  (2025-10-21T06:13:17Z)
• 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)
• Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference [40.96005200292604]
  We present an innovative framework named Sensible and Visionary Commonsense Knowledge (Sibyl)<n>It is designed to concentrate on the immediately succeeding dialogue, aiming to elicit more empathetic responses.<n> Experimental results demonstrate that incorporating our paradigm for acquiring commonsense knowledge into LLMs comprehensively enhances the quality of their responses.
  arXiv  Detail & Related papers  (2023-11-26T14:35:23Z)
• DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback [61.28463542324576]
  We present DRESS, a large vision language model (LVLM) that innovatively exploits Natural Language feedback (NLF) from Large Language Models. We propose a novel categorization of the NLF into two key types: critique and refinement. Our experimental results demonstrate that DRESS can generate more helpful (9.76%), honest (11.52%), and harmless (21.03%) responses.
  arXiv  Detail & Related papers  (2023-11-16T18:37:29Z)
• Controllable Mixed-Initiative Dialogue Generation through Prompting [50.03458333265885]
  Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy planner. Standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents. We instead prompt large language models as a drop-in replacement to fine-tuning on conditional generation.
  arXiv  Detail & Related papers  (2023-05-06T23:11:25Z)
• Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness [62.55060760615656]
  Recent models tackling consistency often train with additional Natural Language Inference (NLI) labels or attach trained extra modules to the generative agent for maintaining consistency. Inspired by social cognition and pragmatics, we endow existing dialogue agents with public self-consciousness on the fly through an imaginary listener. Our approach, based on the Rational Speech Acts framework, can enforce dialogue agents to refrain from uttering contradiction.
  arXiv  Detail & Related papers  (2020-04-13T08:16:16Z)

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.