# Communicate to Play: Pragmatic Reasoning for Efficient Cross-Cultural Communication in Codenames

arXiv: https://arxiv.org/abs/2408.04900 · HTML: https://mlsanity.com/paper/2408.04900/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 9 Aug 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 13 of 13)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking](https://mlsanity.com/paper/2402.09369/) (2024)
- [CultureLLM: Incorporating Cultural Differences into Large Language Models](https://mlsanity.com/paper/2402.10946/) (2024)
- [Aligning to Social Norms and Values in Interactive Narratives](https://mlsanity.com/paper/2205.01975/) (2022)
- [CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge](https://mlsanity.com/paper/2404.06664/) (2024)
- [DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subcultures](https://mlsanity.com/paper/2403.14651/) (2024)
- [CulturePark: Boosting Cross-cultural Understanding in Large Language Models](https://mlsanity.com/paper/2405.15145/) (2024)
- [Context Steering: Controllable Personalization at Inference Time](https://mlsanity.com/paper/2405.01768/) (2024)
- [Modeling Cross-Cultural Pragmatic Inference with Codenames Duet](https://mlsanity.com/paper/2306.02475/) (2023)
- [Large language models can replicate cross-cultural differences in personality](https://mlsanity.com/paper/2310.10679/) (2023)
- [Playing Codenames with Language Graphs and Word Embeddings](https://mlsanity.com/paper/2105.05885/) (2021)

## Built on by (most cited first, 2 of 2)

- [Minding the Politeness Gap in Cross-cultural Communication](https://mlsanity.com/paper/2506.15623/) (2025)
- [Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation](https://mlsanity.com/paper/2604.02557/) (2026)

## Abstract (arXiv)

Cultural differences in common ground may result in pragmatic failure and misunderstandings during communication. We develop our method Rational Speech Acts for Cross-Cultural Communication (RSA+C3) to resolve cross-cultural differences in common ground. To measure the success of our method, we study RSA+C3 in the collaborative referential game of Codenames Duet and show that our method successfully improves collaboration between simulated players of different cultures. Our contributions are threefold: (1) creating Codenames players using contrastive learning of an embedding space and LLM prompting that are aligned with human patterns of play, (2) studying culturally induced differences in common ground reflected in our trained models, and (3) demonstrating that our method RSA+C3 can ease cross-cultural communication in gameplay by inferring sociocultural context from interaction. Our code is publicly available at github.com/icwhite/codenames.