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

• URL: http://arxiv.org/abs/2408.04900v1
• Date: Fri, 9 Aug 2024 07:02:18 GMT
• Title: Communicate to Play: Pragmatic Reasoning for Efficient Cross-Cultural Communication in Codenames
• Authors: Isadora White, Sashrika Pandey, Michelle Pan,
• Abstract summary: We develop our method Rational Speech Acts for Cross-Cultural Communication (RSA+C3) to resolve cross-cultural differences in common ground. We show that our method successfully improves collaboration between simulated players of different cultures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• How Well Do LLMs Identify Cultural Unity in Diversity? [12.982460687543952]
  We introduce a benchmark dataset for evaluating decoder-only large language models (LLMs) in understanding the cultural unity of concepts. CUNIT consists of 1,425 evaluation examples building upon 285 traditional cultural-specific concepts across 10 countries. We design a contrastive matching task to evaluate the LLMs' capability to identify highly associated cross-cultural concept pairs.
  arXiv  Detail & Related papers  (2024-08-09T14:45:22Z)
• CulturePark: Boosting Cross-cultural Understanding in Large Language Models [63.452948673344395]
  This paper introduces CulturePark, an LLM-powered multi-agent communication framework for cultural data collection. It generates high-quality cross-cultural dialogues encapsulating human beliefs, norms, and customs. We evaluate these models across three downstream tasks: content moderation, cultural alignment, and cultural education.
  arXiv  Detail & Related papers  (2024-05-24T01:49:02Z)
• Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense [98.09670425244462]
  Large language models (LLMs) have demonstrated substantial commonsense understanding. This paper examines the capabilities and limitations of several state-of-the-art LLMs in the context of cultural commonsense tasks.
  arXiv  Detail & Related papers  (2024-05-07T20:28:34Z)
• Diversity's Double-Edged Sword: Analyzing Race's Effect on Remote Pair Programming Interactions [0.5999777817331317]
  Mixed-race pairs excelled in task distribution, shared decision-making, and role-exchange but encountered communication challenges, discomfort, and anxiety. Our study emphasizes race's impact on remote pair programming and underscores the need for diverse tools and methods to address racial disparities for collaboration.
  arXiv  Detail & Related papers  (2024-04-11T01:58:38Z)
• Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models [89.94270049334479]
  This paper identifies a cultural dominance issue within large language models (LLMs) LLMs often provide inappropriate English-culture-related answers that are not relevant to the expected culture when users ask in non-English languages.
  arXiv  Detail & Related papers  (2023-10-19T05:38:23Z)
• Modeling Cross-Cultural Pragmatic Inference with Codenames Duet [40.52354928048333]
  This paper introduces the Cultural Codes dataset, which operationalizes sociocultural pragmatic inference in a simple word reference game. Our dataset consists of 794 games with 7,703 turns, distributed across 153 unique players. Our experiments show that accounting for background characteristics significantly improves model performance for tasks related to clue giving and guessing.
  arXiv  Detail & Related papers  (2023-06-04T20:47:07Z)
• The Machine Psychology of Cooperation: Can GPT models operationalise prompts for altruism, cooperation, competitiveness and selfishness in economic games? [0.0]
  We investigated the capability of the GPT-3.5 large language model (LLM) to operationalize natural language descriptions of cooperative, competitive, altruistic, and self-interested behavior. We used a prompt to describe the task environment using a similar protocol to that used in experimental psychology studies with human subjects. Our results provide evidence that LLMs can, to some extent, translate natural language descriptions of different cooperative stances into corresponding descriptions of appropriate task behaviour.
  arXiv  Detail & Related papers  (2023-05-13T17:23:16Z)
• Emergent Communication: Generalization and Overfitting in Lewis Games [53.35045559317384]
  Lewis signaling games are a class of simple communication games for simulating the emergence of language. In these games, two agents must agree on a communication protocol in order to solve a cooperative task. Previous work has shown that agents trained to play this game with reinforcement learning tend to develop languages that display undesirable properties.
  arXiv  Detail & Related papers  (2022-09-30T09:50:46Z)
• Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure [54.01613740115601]
  We study three language properties: constituent order, composition and word co-occurrence. Our main conclusion is that the contribution of constituent order and word co-occurrence is limited, while the composition is more crucial to the success of cross-linguistic transfer.
  arXiv  Detail & Related papers  (2022-03-16T07:09:35Z)
• Emergent Communication under Competition [10.926117869188651]
  We introduce a modified sender-receiver game to study the spectrum of partially-competitive scenarios. We show that communication is proportional to cooperation and it can occur for partially competitive scenarios.
  arXiv  Detail & Related papers  (2021-01-25T17:58:22Z)
• Emergence of Pragmatics from Referential Game between Theory of Mind Agents [64.25696237463397]
  We propose an algorithm, using which agents can spontaneously learn the ability to "read between lines" without any explicit hand-designed rules. We integrate the theory of mind (ToM) in a cooperative multi-agent pedagogical situation and propose an adaptive reinforcement learning (RL) algorithm to develop a communication protocol.
  arXiv  Detail & Related papers  (2020-01-21T19:37:33Z)

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.