mlsanityData to 7 Oct 2026

Continual adaptation for efficient machine communication

arXiv 1911.09896 ↗First posted 22 Nov 2019cs.CLcited by 28

Not on the map. Why?

Abstract (arXiv)

To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent neural language models are able to comprehend and produce the existing conventions present in their training data, but are not able to flexibly and interactively adapt those conventions on the fly as humans do. We introduce an interactive repeated reference task as a benchmark for models of adaptation in communication and propose a regularized continual learning framework that allows an artificial agent initialized with a generic language model to more accurately and efficiently communicate with a partner over time. We evaluate this framework through simulations on COCO and in real-time reference game experiments with human partners.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 5; 2024: 5; 2025: 7; 2026: 4.

28 papers.

Sort:

By area:

  1. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  2. 2021From partners to populations: A hierarchical Bayesian account of coordination and conventioncited by 27
  3. 2022Continual Learning for Instruction Following from Realtime Feedbackcited by 21
  4. 2021Continual Learning for Grounded Instruction Generation by Observing Human Following Behaviorcited by 19
  5. 2024Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMscited by 18
  6. 2021Learning to communicate about shared procedural abstractionscited by 15
  7. 2025Training Language Models for Social Deduction with Multi-Agent Reinforcement Learningcited by 15
  8. 2023How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structurecited by 13
  9. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
  10. 2023Dealing with Semantic Underspecification in Multimodal NLPcited by 9
  11. 2024Natural Language Processing RELIES on Linguisticscited by 9
  12. 2025Measuring How (Not Just Whether) VLMs Build Common Groundcited by 8
16 more
  1. 2026LVLMs and Humans Ground Differently in Referential Communicationcited by 8
  2. 2023Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mindcited by 7
  3. 2024CoGen: Learning from Feedback with Coupled Comprehension and Generationcited by 7
  4. 2025Post-training for Efficient Communication via Convention Formationcited by 7
  5. 2025Success and Cost Elicit Convention Formation for Efficient Communicationcited by 7
  6. 2024Retrospective Learning from Interactionscited by 6
  7. 2023Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoningcited by 4
  8. 2024Policy Learning with a Language Bottleneckcited by 4
  9. 2026Gesturing Toward Abstraction: Multimodal Convention Formation in Collaborative Physical Taskscited by 4
  10. 2021Targeted Data Acquisition for Evolving Negotiation Agentscited by 3
  11. 2022Know your audience: specializing grounded language models with listener subtractioncited by 3
  12. 2025I see what you mean: Co-Speech Gestures for Reference Resolution in Multimodal Dialoguecited by 2
  13. 2025Direct Preference Optimization for Adaptive Concept-based Explanationscited by 0
  14. 2025Ad hoc conventions generalize to new referentscited by 0
  15. 2026Which one is banana man? Evaluating vision-language models in multi-turn pragmatic interpretationcited by 0
  16. 2026Efficient Test-Time Adaptation through Human-AI Interactioncited by 0