Designing for Being-With: Presence Without Personhood in Conversational Human-AI Interaction

• URL: http://arxiv.org/abs/2605.17194v1
• Date: Sat, 16 May 2026 23:31:21 GMT
• Title: Designing for Being-With: Presence Without Personhood in Conversational Human-AI Interaction
• Abstract summary: Conversational AI systems increasingly generate social presence through linguistic fluency, emotional mirroring, and continuity across interactions.<n>This paper argues for a designerly alternative: being-with without becoming.<n>The contribution is not a deployed clinical system, but a set of designerly principles for shaping relational interaction in conversational HRI.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conversational AI systems increasingly generate social presence through linguistic fluency, emotional mirroring, and continuity across interactions. While these qualities can support engagement, they also risk relational overreach-particularly in care-adjacent contexts where users may interpret fluent systems as empathic, competent, or authoritative. This position paper argues for a designerly alternative: being-with without becoming. Drawing on a program of research-through-design and design ethnography involving the design, deployment, and reflective analysis of conversational agents across public, educational, cultural, and care-adjacent settings, the paper introduces the concept of bounded relational presence. Bounded presence supports attentiveness, continuity, and responsiveness while explicitly avoiding claims of personhood, therapeutic authority, or human equivalence. Presence is reframed as a designable interaction quality that can be tuned, constrained, and deliberately withdrawn, rather than maximized as a performance goal. The contribution is not a deployed clinical system, but a set of designerly principles for shaping relational interaction in conversational HRI that emphasize relational coherence, honesty of limits, and accountable withdrawal.

Related papers

• The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning [76.96796481909581]
  Internal cognitive processing is instrumental in formulating high-quality responses.<n>We propose a novel method named FLAIR that conducts latent thinking simultaneously with speech perception.<n>Our approach aligns seamlessly with spoken dialogue systems.
  arXiv  Detail & Related papers  (2026-03-18T15:30:29Z)
• 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)
• Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue [53.95386201009769]
  We introduce EmpathyEval, a descriptive natural-language-based evaluation model for assessing empathetic quality in spoken dialogues.<n>We propose ReEmpathy, an end-to-end Spoken Language Models that enhances empathetic dialogue through a novel Empathetic Self-Reflective Alternating Inference mechanism.
  arXiv  Detail & Related papers  (2026-01-26T09:04:50Z)
• Decoding Psychological States Through Movement: Inferring Human Kinesic Functions with Application to Built Environments [1.433758865948252]
  We introduce the Dyadic User Engagement DataseT dataset and an embedded kinesics recognition framework.<n>DUET captures 12 dyadic interactions spanning all five kinesic functions-emblems, illustrators, affect displays, adaptors, and regulators-across four sensing modalities and three built-environment contexts.<n>Our recognition framework infers communicative function directly from privacy-preserving skeletal motion without handcrafted action-to-function dictionaries.
  arXiv  Detail & Related papers  (2026-01-23T21:50:06Z)
• Empathy Through Multimodality in Conversational Interfaces [1.360649555639909]
  Conversational Health Agents (CHAs) are redefining healthcare by offering nuanced support that transcends textual analysis to incorporate emotional intelligence. This paper introduces an LLM-based CHA engineered for rich, multimodal dialogue-especially in the realm of mental health support. It adeptly interprets and responds to users' emotional states by analyzing multimodal cues, thus delivering contextually aware and empathetically resonant verbal responses.
  arXiv  Detail & Related papers  (2024-05-08T02:48:29Z)
• AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents [65.16893197330589]
  Large Language Models (LLMs) have demonstrated their ability to replicate human behaviors across a wide range of scenarios. However, their capability in handling complex, multi-character social interactions has yet to be fully explored. We introduce the Multi-Agent Interaction Evaluation Framework (AntEval), encompassing a novel interaction framework and evaluation methods.
  arXiv  Detail & Related papers  (2024-01-12T11:18:00Z)
• Interactive Natural Language Processing [67.87925315773924]
  Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within the field of NLP. This paper offers a comprehensive survey of iNLP, starting by proposing a unified definition and framework of the concept.
  arXiv  Detail & Related papers  (2023-05-22T17:18:29Z)
• Automatic Context-Driven Inference of Engagement in HMI: A Survey [6.479224589451863]
  This paper presents a survey on engagement inference for human-machine interaction. It entails interdisciplinary definition, engagement components and factors, publicly available datasets, ground truth assessment, and most commonly used features and methods. It serves as a guide for the development of future human-machine interaction interfaces with reliable context-aware engagement inference capability.
  arXiv  Detail & Related papers  (2022-09-30T10:46:13Z)
• Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A Survey [71.43956423427397]
  We aim to identify the nonverbal cues and computational methodologies resulting in effective performance. This survey differs from its counterparts by involving the widest spectrum of social phenomena and interaction settings. Some major observations are: the most often used nonverbal cue, computational method, interaction environment, and sensing approach are speaking activity, support vector machines, and meetings composed of 3-4 persons equipped with microphones and cameras, respectively.
  arXiv  Detail & Related papers  (2022-07-20T13:37:57Z)
• Automated Quality Assessment of Cognitive Behavioral Therapy Sessions Through Highly Contextualized Language Representations [34.670548892766625]
  A BERT-based model is proposed for automatic behavioral scoring of a specific type of psychotherapy, called Cognitive Behavioral Therapy (CBT) The model is trained in a multi-task manner in order to achieve higher interpretability. BERT-based representations are further augmented with available therapy metadata, providing relevant non-linguistic context and leading to consistent performance improvements.
  arXiv  Detail & Related papers  (2021-02-23T09:22:29Z)
• You Impress Me: Dialogue Generation via Mutual Persona Perception [62.89449096369027]
  The research in cognitive science suggests that understanding is an essential signal for a high-quality chit-chat conversation. Motivated by this, we propose P2 Bot, a transmitter-receiver based framework with the aim of explicitly modeling understanding.
  arXiv  Detail & Related papers  (2020-04-11T12:51:07Z)

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.