Conversational Agents and the Understanding of Human Language: Reflections on AI, LLMs, and Cognitive Science

Andrei Popescu-Belis

cs.CLMar 29, 2026

Conversational Agents and the Understanding of Human Language: Reflections on AI, LLMs, and Cognitive Science

Authors: Andrei Popescu-Belis

Organizations: HEIG-VD / HES-SO, 1401 Yverdon-les-Bains, Switzerland · EPFL, 1015 Lausanne, Switzerland

Abstract

In this paper, we discuss the relationship between natural language processing by computers (NLP) and the understanding of the human language capacity, as studied by linguistics and cognitive science. We outline the evolution of NLP from its beginnings until the age of large language models, and highlight for each of its main paradigms some similarities and differences with theories of the human language capacity. We conclude that the evolution of language technology has not substantially deepened our understanding of how human minds process natural language, despite the impressive language abilities attained by current chatbots using artificial neural networks.

Figures & tables

Panel of Figure 1 — Figure 1: Two simple structures of artificial neural networks that have been used to designed early neural language models. The core idea of such networks is that the activation of each unit is a function (often non linear) of the weighted sum of the activations of units connected to it.

Conversational Agents

Conversational agents are AI systems that interact with people through multi-turn dialogue to answer questions, provide support, or complete tasks.

See all 287 papers

Understanding Large Language Models
Jul 1, 2026Yannik Keller, Thomas EisenmannEmergent Abilities in Language Models LLM Interpretability
Some hypotheses on how chatbots work in problem-solution-driven conversations: Large Language Models as confirmation of the Innovation Illusion
Jun 5, 2026S. F. M. van Vlijmen, H. D. Lethe jrCognitive Modeling Conversational Agents
LLM and Human Modes of Representation
Jun 19, 2026Shalom LappinLLM Evaluation LLM Reasoning
Queen Mary University of London and King’s College London

Jul 1, 2026J/K move · Enter open · S save

Understanding Large Language Models

Yannik Keller, Thomas Eisenmann

Emergent Abilities in Language Models LLM Interpretability

Open paper AskPDF arXiv

Large Language Models (LLMs) represent one of the most significant advances in AI and natural language processing in recent years. Still, many pressing questions about their mechanisms, capabilities, and relationship to human cognition remain highly debated. This chapter aims to outline our current understanding of LLMs by discussing recent evidence on emerging capabilities and their mechanistic implementation within processing layers. We begin with a concise overview of the Transformer architecture, emphasizing how the attention mechanism enables training on massive datasets, allowing LLMs to function as generalist rather than specialized models. Next, we examine emergent LLM capabilities that appear to resemble aspects of human cognition, including symbolic reasoning, theory of mind, and deception strategies. Several studies provide evidence that LLMs can solve tasks previously thought to require human-like cognition. Other studies reveal insightful failure cases that shed light on the differences between human and LLM cognition. Alongside these findings, we review explainable AI approaches ranging from neuron activation analysis to circuit tracing. In the final section, we address current debates concerning what LLMs genuinely understand versus what they merely appear to understand. Prominent arguments against AI anthropomorphism point to the simplicity of LLM training objectives, claiming that LLM behavior is better explained by pattern memorization of training data than by genuine cognition. We argue that this standpoint is guided by misconceptions about optimization processes and cognitive capacity, and advocate for a more nuanced discussion of LLM cognition that neither dismisses the differences between humans and LLMs nor precludes the possibility of AI cognition through overly simplistic reductionist arguments.

Abstract

Conversational Agents

Explore similar work

Understanding Large Language Models

Some hypotheses on how chatbots work in problem-solution-driven conversations: Large Language Models as confirmation of the Innovation Illusion

LLM and Human Modes of Representation