mlsanityData to 14 Oct 2026

Learning to Mediate Disparities Towards Pragmatic Communication

arXiv 2203.13685 ↗First posted 25 Mar 2022cs.CL cs.AI cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Human communication is a collaborative process. Speakers, on top of conveying their own intent, adjust the content and language expressions by taking the listeners into account, including their knowledge background, personalities, and physical capabilities. Towards building AI agents with similar abilities in language communication, we propose Pragmatic Rational Speaker (PRS), a framework extending Rational Speech Act (RSA). The PRS attempts to learn the speaker-listener disparity and adjust the speech accordingly, by adding a light-weighted disparity adjustment layer into working memory on top of speaker's long-term memory system. By fixing the long-term memory, the PRS only needs to update its working memory to learn and adapt to different types of listeners. To validate our framework, we create a dataset that simulates different types of speaker-listener disparities in the context of referential games. Our empirical results demonstrate that the PRS is able to shift its output towards the language that listener are able to understand, significantly improve the collaborative task outcome.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 20 of its 41 references that are in the map. First posted on arXiv 25 Mar 2022.

Builds on

20 of 41 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2018YOLOv3: An Incremental Improvementcited by 2,659
  3. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  4. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  5. 2018Speaker-Follower Models for Vision-and-Language Navigationcited by 340
  6. 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 170
  7. 2017Grounded Language Learning in a Simulated 3D Worldcited by 100
  8. 2017Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialogcited by 86
  9. 2016Reasoning About Pragmatics with Neural Listeners and Speakerscited by 68
  10. 2020Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learningcited by 66
  11. 2021MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Taskscited by 62
  12. 2017Unified Pragmatic Models for Generating and Following Instructionscited by 55
8 more
  1. 2018Pragmatically Informative Image Captioning with Character-Level Inferencecited by 42
  2. 2021Few-shot Language Coordination by Modeling Theory of Mindcited by 32
  3. 2021From partners to populations: A hierarchical Bayesian account of coordination and conventioncited by 27
  4. 2020Learning to refer informatively by amortizing pragmatic reasoningcited by 17
  5. 2015Learning in the Rational Speech Acts Modelcited by 16
  6. 2017Understanding Early Word Learning in Situated Artificial Agentscited by 8
  7. 2019Know What You Don't Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categoriescited by 8
  8. 2019Modeling Conceptual Understanding in Image Reference Gamescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 1; 2025: 2; 2026: 3.

14 papers.

Sort:

By area:

  1. 2026Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisonscited by 60
  2. 2023Towards A Holistic Landscape of Situated Theory of Mind in Large Language Modelscited by 32
  3. 2025Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challengescited by 31
  4. 2023Modeling Cross-Cultural Pragmatic Inference with Codenames Duetcited by 20
  5. 2024Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialoguecited by 11
  6. 2025Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generationcited by 8
  7. 2022Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for Instruction Generation Modelscited by 7
  8. 2023Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mindcited by 7
  9. 2023Which One? Leveraging Context Between Objects and Multiple Views for Language Groundingcited by 3
  10. 2023Discourse over Discourse: The Need for an Expanded Pragmatic Focus in Conversational AIcited by 1
  11. 2023Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisitioncited by 1
  12. 2023Expanding the Set of Pragmatic Considerations in Conversational AIcited by 0
2 more
  1. 2026Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluationcited by 0
  2. 2026Which one is banana man? Evaluating vision-language models in multi-turn pragmatic interpretationcited by 0