Reconsidering Conversational Norms in LLM Chatbots for Sustainable AI

• URL: http://arxiv.org/abs/2512.14673v1
• Date: Tue, 16 Dec 2025 18:38:11 GMT
• Title: Reconsidering Conversational Norms in LLM Chatbots for Sustainable AI
• Abstract summary: We argue that interaction level behavior appears to be an underexamined factor shaping the environmental impact of LLM based systems.<n>We show how extended conversational patterns increase token production and raise the computational cost of inference.<n>We argue that everyday user habits contribute to cumulative operational demand in ways that are rarely quantified.
• Score: 2.198430261120653
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI [74.72113315839412]
  Large Language Models (LLMs) are undergoing a fundamental transformation into integrated AI systems capable of reasoning, memory, and self-improvement.<n>We conceptualize this transition as a shift from episodic to Digital Colleague: from conversational answers to persistent work.
  arXiv  Detail & Related papers  (2026-06-12T14:33:55Z)
• LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning [6.96644195073436]
  We develop a framework for task-oriented dialogues grounded in realistic reasoning scenarios.<n>Our method generates dialogues grounded in authentic task scenarios, enriched with real-world information.<n>The resulting dataset serves as a valuable benchmark for assessing and advancing the realistic logical reasoning capabilities of large language models.
  arXiv  Detail & Related papers  (2026-02-27T02:23:37Z)
• ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding [4.5799194788369455]
  bench is the first dynamic, live evaluation benchmark specifically designed for intent understanding, particularly in the consumer domain.<n>bench is the largest and most diverse benchmark of its kind, supporting real-time updates while preventing data contamination through an automated curation pipeline.
  arXiv  Detail & Related papers  (2025-10-15T12:49:45Z)
• KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues [58.305425399644086]
  Multi-Turn Long-Form Question Answering (MT-LFQA) is a key application paradigm of Large Language Models (LLMs) in knowledge-intensive domains.<n>We introduce textbfKnowMT-Bench, the textitfirst-ever benchmark designed to systematically evaluate MT-LFQA for LLMs across knowledge-intensive fields.
  arXiv  Detail & Related papers  (2025-09-26T04:32:29Z)
• Mitigating the Carbon Footprint of Chatbots as Consumers [7.237493755167876]
  This paper examines the environmental impact linked to a fundamental function of large language models (LLMs)<n>After analyzing conversation patterns using anonymized token data from a real world system, a recommendation for individuals on how they could use chatbots in a more sustainable way is derived.<n>Based on a simulation, the savings potential resulting from the adoption of such an ecological gesture is estimated.
  arXiv  Detail & Related papers  (2025-07-29T19:00:43Z)
• When LLMs Team Up: The Emergence of Collaborative Affective Computing [17.777196145195866]
  This survey aims to provide a comprehensive overview of Large Language Models (LLMs)-based collaboration systems in Affective Computing (AC)<n>LLMs offer a unified approach to affective understanding and generation tasks, enhancing the potential for dynamic, real-time interactions.<n>This work is the first to systematically explore collaborative intelligence with LLMs in AC, paving the way for more powerful applications that approach human-like social intelligence.
  arXiv  Detail & Related papers  (2025-06-02T14:00:54Z)
• Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes [84.1059652774853]
  Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks.<n>Recent studies have exposed critical limitations in their spatial reasoning capabilities.<n>This deficiency in spatial reasoning significantly constrains MLLMs' ability to interact effectively with the physical world.
  arXiv  Detail & Related papers  (2025-04-21T11:48:39Z)
• Enabling Real-Time Conversations with Minimal Training Costs [61.80370154101649]
  This paper presents a new duplex decoding approach that enhances large language models with duplex ability, requiring minimal training. Experimental results indicate that our proposed method significantly enhances the naturalness and human-likeness of user-AI interactions with minimal training costs.
  arXiv  Detail & Related papers  (2024-09-18T06:27:26Z)
• Constraining Participation: Affordances of Feedback Features in Interfaces to Large Language Models [49.266685603250416]
  Large language models (LLMs) are now accessible to anyone with a computer, a web browser, and an internet connection via browser-based interfaces.<n>This article examines how interactive feedback features in ChatGPT's interface afford user participation in LLMs.
  arXiv  Detail & Related papers  (2024-08-27T13:50:37Z)
• Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making [51.737762570776006]
  LLM-ACTR is a novel neuro-symbolic architecture that provides human-aligned and versatile decision-making. Our framework extracts and embeds knowledge of ACT-R's internal decision-making process as latent neural representations. Our experiments on novel Design for Manufacturing tasks show both improved task performance as well as improved grounded decision-making capability.
  arXiv  Detail & Related papers  (2024-08-17T11:49:53Z)
• Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis [22.755345889167934]
  We present an interactive visualization system that enables exploration of large language models (LLMs) through counterfactual analysis.<n>Our system features a novel algorithm that generates fluent and semantically meaningful counterfactuals.<n>A user study with LLM practitioners and interviews with experts demonstrate the system's usability and effectiveness.
  arXiv  Detail & Related papers  (2024-04-23T19:57:03Z)
• Conversational Assistants in Knowledge-Intensive Contexts: An Evaluation of LLM- versus Intent-based Systems [8.88228247647452]
  Large Language Models (LLMs) enable Conversational Assistants (CAs) to converse in a more flexible, human-like manner. LLMs exhibited better user experience, task completion rate, usability, and perceived performance than intent-based systems.
  arXiv  Detail & Related papers  (2024-02-07T15:39:07Z)
• Building Emotional Support Chatbots in the Era of LLMs [64.06811786616471]
  We introduce an innovative methodology that synthesizes human insights with the computational prowess of Large Language Models (LLMs) By utilizing the in-context learning potential of ChatGPT, we generate an ExTensible Emotional Support dialogue dataset, named ExTES. Following this, we deploy advanced tuning techniques on the LLaMA model, examining the impact of diverse training strategies, ultimately yielding an LLM meticulously optimized for emotional support interactions.
  arXiv  Detail & Related papers  (2023-08-17T10:49:18Z)
• Approximating Online Human Evaluation of Social Chatbots with Prompting [11.657633779338724]
  Existing evaluation metrics aim to automate offline user evaluation and approximate human judgment of pre-curated dialogs. We propose an approach to approximate online human evaluation leveraging large language models (LLMs) from the GPT family. We introduce a new Dialog system Evaluation framework based on Prompting (DEP), which enables a fully automatic evaluation pipeline.
  arXiv  Detail & Related papers  (2023-04-11T14:45:01Z)

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.