Reconsidering Conversational Norms in LLM Chatbots for Sustainable AI

TL;DR

The paper investigates how interaction design and user behavior influence the energy footprint of LLM-based chatbots, arguing that sustainable AI must extend beyond hardware and model optimizations to include dialogue patterns, immediacy expectations, and context management. It synthesizes evidence on token throughput, real-time workloads, and context growth to argue that longer outputs, persistent histories, and high interaction volumes can significantly increase energy use. Through four analytical dimensions, it identifies concrete research opportunities—metrics, selective reasoning, adaptive invocation, user guidance, and sustainable context management—to reduce waste without compromising utility. The work highlights the potential of software-layer interventions and demand-side strategies as practical levers for greener AI in software engineering and education contexts. Overall, it reframes sustainability as a property of conversational norms and interaction design, urging a balanced approach that complements infrastructural improvements with user-facing, behavior-aware solutions.

Abstract

LLM based chatbots have become central interfaces in technical, educational, and analytical domains, supporting tasks such as code reasoning, problem solving, and information exploration. As these systems scale, sustainability concerns have intensified, with most assessments focusing on model architecture, hardware efficiency, and deployment infrastructure. However, existing mitigation efforts largely overlook how user interaction practices themselves shape the energy profile of LLM based systems. In this vision paper, we argue that interaction level behavior appears to be an underexamined factor shaping the environmental impact of LLM based systems, and we present this issue across four dimensions. First, extended conversational patterns increase token production and raise the computational cost of inference. Second, expectations of instant responses limit opportunities for energy aware scheduling and workload consolidation. Third, everyday user habits contribute to cumulative operational demand in ways that are rarely quantified. Fourth, the accumulation of context affects memory requirements and reduces the efficiency of long running dialogues. Addressing these challenges requires rethinking how chatbot interactions are designed and conceptualized, and adopting perspectives that recognize sustainability as partly dependent on the conversational norms through which users engage with LLM based systems.