mlsanityData to 14 Oct 2026

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

arXiv 2602.08208 ↗First posted 9 Feb 2026cs.CL cs.HCcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 8 of its 29 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

8 of 29 references.

References · 8

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  4. 2022Talking About Large Language Modelscited by 175
  5. 2025Large Language Models Pass the Turing Testcited by 48
  6. 2025On the generalization of language models from in-context learning and finetuning: a controlled studycited by 40
  7. 2026LVLMs and Humans Ground Differently in Referential Communicationcited by 8
  8. 2025Success and Cost Elicit Convention Formation for Efficient Communicationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactionscited by 1
  2. 2026Implicit vs. Explicit Prompting Strategies for LVLMs in Referential Communicationcited by 0
  3. 2026When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMscited by 0
  4. 2026Which one is banana man? Evaluating vision-language models in multi-turn pragmatic interpretationcited by 0
  5. 2026Talking Past the Machine: Morality, Politeness, and Alignment in Human-AI Dialoguecited by 0