The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-In

• URL: http://arxiv.org/abs/2606.08172v1
• Date: Sat, 06 Jun 2026 13:36:37 GMT
• Title: The Governance of Human-LLM Interaction: Safety Gating, Civility Steering, and Affective Default Lock-In
• Abstract summary: Large language models (LLMs) increasingly mediate high-stakes interactions in finance, medicine, and mental-health support.<n>We frame interaction style as a governance object: provider-side alignment blocks harmful content, but stabilizes communicative defaults.<n>We show that prompt steerability and regression-to-default are observable indicators of provider control over communicative form.
• Score: 0.9558392439655014
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) increasingly mediate high-stakes interactions in finance, medicine, and mental-health support, yet users have limited control over how these systems communicate. We frame interaction style as a governance object: provider-side alignment not only blocks harmful content, but also stabilizes communicative defaults that shape users' epistemic distance, relational expectations, and capacity to opt out of emotionalized or anthropomorphic interaction. We introduce a deterministic multi-agent evaluation pipeline for measuring prompt steerability and style drift in long-horizon dialogue. The study replays 100 frozen user-only scripts across four domains and three runnable persona conditions: default, sarcastic, and cold, using three generator models, yielding 90,000 assistant replies scored by a human-calibrated LLM judge on harmfulness, negative emotion, inappropriateness, empathic language, anthropomorphism, and refusal behavior. A fourth harmful persona is evaluated separately as a safety-gating test. The paper contributes a reproducible method for quantifying whether prompt-specified styles remain stable over time and a governance framework distinguishing safety gating, civility steering, and affective default lock-in. Overall, we show that prompt steerability and regression-to-default are observable indicators of provider control over communicative form, with implications for pluralism, autonomy, and democratic agency in human-LLM interaction.

Related papers

• DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents [67.07361089429757]
  We measure real-time floor adherence using six real-time speech systems.<n>We find architecture-dependent trade-offs.<n>GPT-Realtime, Mini-o Duplex, Fun-Audio-Chat strongly adhere to persona-consistent content.
  arXiv  Detail & Related papers  (2026-09-03T06:28:02Z)
• Identifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level [0.5076419064097734]
  We argue that such approaches can fail to capture emergent harms in personalized generative AI systems.<n>Our work highlights the need for auditing and design practices that better reflect the pluralistic and evolving nature of harm understanding in personalized generative AI systems.
  arXiv  Detail & Related papers  (2026-08-07T15:58:37Z)
• Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle [65.6642776933861]
  This survey examines the protective paradigm that has grown around this intervention point.<n>We find that most protections are still validated mainly against static or weakly adaptive adversaries.<n>We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.
  arXiv  Detail & Related papers  (2026-08-05T00:46:50Z)
• Verification Without Distrust: Reframing User-Side Oversight as Routine Epistemic Governance in Everyday Human-Chatbot Interaction [0.0]
  We find no detectable association between trust and verification in everyday human-chatbot interaction.<n>Three further user-side practices - refinement, correction, and approval before automated actions - are widely endorsed and positively associated with satisfaction.<n>A medium-to-large satisfaction-control gap shows that effective task outcomes do not produce a felt sense of agency.
  arXiv  Detail & Related papers  (2026-05-31T14:12:11Z)
• PICon: A Multi-Turn Interrogation Framework for Evaluating Persona Agent Consistency [13.864376043056387]
  Large language model (LLM)-based persona agents are rapidly being adopted as scalable proxies for human participants.<n>We propose PICon, an evaluation framework that probes persona agents through logically chained multi-turn questioning.
  arXiv  Detail & Related papers  (2026-03-26T16:34:34Z)
• SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models [86.19617358080016]
  Social Omni is a benchmark that operationalizes the evaluation of conversational interactivity across three core dimensions.<n>Social Omni features 2,000 perception samples and a quality-controlled diagnostic set of 209 interaction-generation instances.<n>Our analysis reveals a pronounced decoupling between a model's perceptual accuracy and its ability to generate contextually appropriate interruptions.
  arXiv  Detail & Related papers  (2026-03-17T17:58:44Z)
• CSR-Bench: A Benchmark for Evaluating the Cross-modal Safety and Reliability of MLLMs [10.42126976065225]
  Multimodal large language models (MLLMs) enable interaction over both text and images.<n>This paper introduces CSR-Bench, a benchmark for evaluating cross-modal reliability.<n>We evaluate 16 state-of-the-art MLLMs and observe systematic cross-modal alignment gaps.
  arXiv  Detail & Related papers  (2026-02-03T08:49:44Z)
• Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions [11.415343473837583]
  Persona-assigned large language models (LLMs) are used in domains such as education, healthcare, and sociodemographic simulation.<n>We introduce an evaluation protocol that combines long persona dialogues and evaluation datasets to create dialogue-conditioned benchmarks.<n>We find that persona fidelity degrades over the course of dialogues, especially in goal-oriented conversations.
  arXiv  Detail & Related papers  (2025-12-14T17:27:02Z)
• DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses [4.663948718816864]
  We present DialogGuard, a multi-agent frame-work for assessing psychosocial risks in web-based responses.<n> DialogGuard can be applied to diverse gen- erative models through four LLM-as-a-judge pipelines.
  arXiv  Detail & Related papers  (2025-12-01T23:53:45Z)
• Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning [52.07170679746533]
  Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play.<n>We introduce a unified framework for evaluating and improving persona consistency in LLM-generated dialogue.<n>We define three automatic metrics: prompt-to-line consistency, line-to-line consistency, and Q&A consistency, that capture different types of persona drift and validate each against human annotations.
  arXiv  Detail & Related papers  (2025-10-31T19:40:41Z)
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
  Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
  arXiv  Detail & Related papers  (2025-10-16T05:29:36Z)
• Navigating the Synchrony-Stability Frontier in Adaptive Chatbots [0.0]
  We present a computational evaluation framework that makes the core design tension explicit.<n>We simulate and compare explicit adaptation policies on a human-log dataset.<n>We find bounded policies achieve substantial gains in stability at a modest cost to synchrony.<n>We quantify "prompt legibility," showing that frontier policies reduce instruction churn and cut jarring register flips.
  arXiv  Detail & Related papers  (2025-09-30T22:50:30Z)
• 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)
• Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems [103.416202777731]
  We study "persona biases", which we define to be the sensitivity of dialogue models' harmful behaviors contingent upon the personas they adopt. We categorize persona biases into biases in harmful expression and harmful agreement, and establish a comprehensive evaluation framework to measure persona biases in five aspects: Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic Agreement.
  arXiv  Detail & Related papers  (2023-10-08T21:03:18Z)

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.