How to start a conversation proactively?
cs.HC, cs.LG, cs.RO
Submitted: 2026-08-22
Updated: 2026-08-22
Comments: The article is accepted in IEEE RO-MAN 2026. The dataset is available at https://github.com/mohit-nathani1/conversation-opener-dataset
Code: https://github.com/mohit-nathani1/conversation-opener-dataset
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Proactively initiating a conversation is a fundamental social competence and a critical capability for social robots.
Abstract
Proactively initiating a conversation is a fundamental social competence and a critical capability for social robots. However, determining how and when to start a conversation in a given situation remains an open challenge, primarily due to the lack of a principled definition of conversational context. While recent large language models (LLMs) demonstrate impressive conversational fluency, they are predominantly turn-reactive and often produce generic or monotonous openers when tasked with initiating interaction, even when contextual information is available. Such limitations are particularly problematic for embodied social robots, where inappropriate or poorly timed initiations can negatively affect user engagement and rapport. In this work, we propose a schema of contextual variables that jointly characterize situations relevant for proactive conversation initiation. The schema is designed to structure perceptual, situational, and interactional cues such that they can be effectively exploited by language models. Furthermore, motivated by the absence of suitable training data, we introduce a curated dataset of contextually-aligned conversation openers (CCO) covering diverse everyday scenarios. Using this dataset, we fine-tune small language models (SLMs) to generate proactive conversation initiations. Through a comparative evaluation involving zero-shot LLMs, off-the-shelf SLMs, and our fine-tuned models, we demonstrate that explicit contextual structuring and targeted data curation substantially improve the quality and contextual appropriateness of conversation openers. Our results highlight the importance of context modeling for proactive social interaction and provide actionable building blocks for conversational robots.
Sources
- Verbal tics in frontier language models: A critical review of current releases, research evidence, and public discussion
- BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
- FlowAct: A Proactive Multimodal Human-robot Interaction System with Continuous Flow of Perception and Modular Action Sub-systems
- Personalizing Emotion-aware Conversational Agents? Exploring User Traits-driven Conversational Strategies for Enhanced Interaction
- The Llama 3 Herd of Models
- Gemma: Open Models Based on Gemini Research and Technology
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- BERTScore: Evaluating Text Generation with BERT
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems