LLMs and people both learn to form conventions -- just not with each other

• URL: http://arxiv.org/abs/2602.08208v1
• Date: Mon, 09 Feb 2026 02:15:18 GMT
• Title: LLMs and people both learn to form conventions -- just not with each other
• Abstract summary: Humans align to one another in conversation -- adopting shared conventions that ease communication.<n>We test whether LLMs form the same kinds of conventions in a multimodal communication game.
• Score: 13.170148649113775
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Humans align to one another in conversation -- adopting shared conventions that ease communication. We test whether LLMs form the same kinds of conventions in a multimodal communication game. Both humans and LLMs display evidence of convention-formation (increasing the accuracy and consistency of their turns while decreasing their length) when communicating in same-type dyads (humans with humans, AI with AI). However, heterogenous human-AI pairs fail -- suggesting differences in communicative tendencies. In Experiment 2, we ask whether LLMs can be induced to behave more like human conversants, by prompting them to produce superficially humanlike behavior. While the length of their messages matches that of human pairs, accuracy and lexical overlap in human-LLM pairs continues to lag behind that of both human-human and AI-AI pairs. These results suggest that conversational alignment requires more than just the ability to mimic previous interactions, but also shared interpretative biases toward the meanings that are conveyed.

Related papers

• Do LLMs Change Their Minds Like Humans? Diagnosing Human--LLM Divergence in Single-Turn Persuasion Judgments [10.717755637740948]
  Large language models (LLMs) are increasingly deployed as proxies for human participants in social simulations.<n>We conduct a systematic comparison using a naturally occurring online persuasion corpus.<n>Our results show that LLMs achieve only slight agreement with humans.
  arXiv  Detail & Related papers  (2026-08-30T14:08:06Z)
• LVLMs and Humans Ground Differently in Referential Communication [33.82075906105276]
  We present a factorial design involving director-matcher pairs that interact with multiple turns in repeated rounds to match pictures of objects not associated with any obvious lexicalized labels.<n>We release the online pipeline for data collection, the tools and analyses for accuracy, efficiency, and lexical overlap, and a corpus of 356 dialogues that unmasks LVLMs' limitations in interactively resolving referring expressions.
  arXiv  Detail & Related papers  (2026-01-27T16:52:20Z)
• Mind the Gap: Linguistic Divergence and Adaptation Strategies in Human-LLM Assistant vs. Human-Human Interactions [14.21024646209994]
  Large Language Models (LLMs) are increasingly deployed in customer-facing applications.<n>Our study shows significant differences in grammatical fluency, politeness, and lexical diversity in user language between the two settings.<n>To enhance robustness to post-launch communication style changes, we experimented with two strategies.
  arXiv  Detail & Related papers  (2025-10-03T00:45:37Z)
• Shaping Shared Languages: Human and Large Language Models' Inductive Biases in Emergent Communication [0.09999629695552195]
  We investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs)<n>We show that referentially grounded vocabularies emerge that enable reliable communication in all conditions, even when humans collaborate.
  arXiv  Detail & Related papers  (2025-03-06T12:47:54Z)
• AI persuading AI vs AI persuading Humans: LLMs' Differential Effectiveness in Promoting Pro-Environmental Behavior [70.24245082578167]
  Pro-environmental behavior (PEB) is vital to combat climate change, yet turning awareness into intention and action remains elusive.<n>We explore large language models (LLMs) as tools to promote PEB, comparing their impact across 3,200 participants.<n>Results reveal a "synthetic persuasion paradox": synthetic and simulated agents significantly affect their post-intervention PEB stance, while human responses barely shift.
  arXiv  Detail & Related papers  (2025-03-03T21:40:55Z)
• Trying to be human: Linguistic traces of stochastic empathy in language models [0.2638512174804417]
  Large language models (LLMs) are crucial drivers behind the increased quality of computer-generated content. Our work tests how two important factors contribute to the human vs AI race: empathy and an incentive to appear human.
  arXiv  Detail & Related papers  (2024-10-02T15:46:40Z)
• X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents [56.64615470513102]
  The Turing test examines whether AIs exhibit human-like behaviour in natural language conversations.<n>Traditional setting limits each participant to one message at a time and requires constant human participation.<n>This paper proposes textbftextscX-Turing, which enhances the original test with a textitburst dialogue pattern.
  arXiv  Detail & Related papers  (2024-08-19T09:57:28Z)
• Strong and weak alignment of large language models with human values [1.6590638305972631]
  Minimizing negative impacts of Artificial Intelligent (AI) systems requires them to be able to align with human values. We argue that this is required for AI systems like large language models (LLMs) to be able to recognize situations presenting a risk that human values may be flouted. We propose a new thought experiment that we call "the Chinese room with a word transition dictionary", in extension of John Searle's famous proposal.
  arXiv  Detail & Related papers  (2024-08-05T11:27:51Z)
• Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance [73.19687314438133]
  We study how reliance is affected by contextual features of an interaction. We find that contextual characteristics significantly affect human reliance behavior. Our results show that calibration and language quality alone are insufficient in evaluating the risks of human-LM interactions.
  arXiv  Detail & Related papers  (2024-07-10T18:00:05Z)
• Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment [84.32768080422349]
  Alignment with human preference prevents large language models from generating misleading or toxic content. We propose a new formulation of prompt diversity, implying a linear correlation with the final performance of LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2024-03-17T07:08:55Z)
• Divergences between Language Models and Human Brains [59.100552839650774]
  We systematically explore the divergences between human and machine language processing.<n>We identify two domains that LMs do not capture well: social/emotional intelligence and physical commonsense.<n>Our results show that fine-tuning LMs on these domains can improve their alignment with human brain responses.
  arXiv  Detail & Related papers  (2023-11-15T19:02:40Z)
• Towards Abstract Relational Learning in Human Robot Interaction [73.67226556788498]
  Humans have a rich representation of the entities in their environment. If robots need to interact successfully with humans, they need to represent entities, attributes, and generalizations in a similar way. In this work, we address the problem of how to obtain these representations through human-robot interaction.
  arXiv  Detail & Related papers  (2020-11-20T12:06:46Z)

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.