No article text was recorded for this version.
language drift
Version 1 of 179 papers98 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Community Regularization of Visually-Grounded Dialog
- Blog: Interactive Reinforcement Learning for Object Grounding via Self-Talking
- Blog: Countering Language Drift with Seeded Iterated Learning
- Blog: Countering Language Drift with Seeded Iterated Learning
- Blog: Decoupling Strategy and Generation in Negotiation Dialogues
- Blog: On the interaction between supervision and self-play in emergent communication
- Blog: Deal or No Deal? End-to-End Learning for Negotiation Dialogues
- Blog: Seeded self-play for language learning
- Blog: Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat
- Blog: Evaluating Visual Conversational Agents via Cooperative Human-AI Games
- Blog: Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning
- Blog: GPT-Critic: Offline Reinforcement Learning for End-to-End Task-Oriented Dialogue Systems
- Blog: Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability
- Blog: Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition
- Blog: Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning
- Blog: CoGen: Learning from Feedback with Coupled Comprehension and Generation
- Blog: Deal or No Deal? End-to-End Learning of Negotiation Dialogues
- Blog: Hierarchical Text Generation and Planning for Strategic Dialogue
- Blog: Adapting LLM Agents Through Communication
- Blog: Bayes-Adaptive Monte-Carlo Planning and Learning for Goal-Oriented Dialogues
- Blog: On Emergent Communication in Competitive Multi-Agent Teams
- Blog: Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both
- Blog: Modeling the Interaction Between Perception-Based and Production-Based Learning in Children’s Early Acquisition of Semantic Knowledge
- Blog: Targeted Data Acquisition for Evolving Negotiation Agents
- Blog: RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs
- Blog: Diverse Audio Captioning via Adversarial Training
- Blog: CoGen: Learning from Feedback with Coupled Comprehension and Generation
- Blog: Interpretable Multi-Agent Communication via Information Gating
- Blog: CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication
- Blog: An Encoder-Decoder Based Audio Captioning System with Transfer and Reinforcement Learning
- Blog: Inference-Based Deterministic Messaging For Multi-Agent Communication
- Blog: Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting
- Blog: AirDialogue: An Environment for Goal-Oriented Dialogue Research
- Blog: Language Model Alignment with Elastic Reset
- Blog: Language Grounded Multi-agent Communication for Ad-hoc Teamwork
- Blog: Shaped Rewards Bias Emergent Language
- Blog: Reasoning Models Sometimes Output Illegible Chains of Thought
- Blog: Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data
- Blog: Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play
- Blog: Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
- Blog: Multitasking Inhibits Semantic Drift
- Blog: Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models
- Blog: From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation
- Blog: RMM: A Recursive Mental Model for Dialog Navigation
- Blog: I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents
- Blog: Language Model Alignment with Elastic Reset
- Blog: Cross-Domain Image Captioning with Discriminative Finetuning
- Blog: Dynamic population-based meta-learning for multi-agent communication with natural language
- Blog: Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment
- Blog: Revisiting Populations in multi-agent Communication
- Blog: Semantics and Spatiality of Emergent Communication
- Blog: Supervised Seeded Iterated Learning for Interactive Language Learning
- Blog: Improving Goal-Oriented Visual Dialog Agents via Advanced Recurrent Nets with Tempered Policy Gradient
- Blog: A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization
- Blog: Calibrate your listeners! Robust communication-based training for pragmatic speakers
- Blog: Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention
- Blog: Distinctive Image Captioning via CLIP Guided Group Optimization
- Blog: Competitive Bridge Bidding with Deep Neural Networks
- Blog: Evaluating pragmatic abilities of image captioners on A3DS
- Blog: RMM: A Recursive Mental Model for Dialog Navigation
Showing 60 of 79 papers.
History & citation
Current · Permanent link
- Preventing Language Drift in Task Oriented Dialogue merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_language_drift_d6ffbf87,
title = {language drift},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/language-drift/rdr_d6ffbf87f4fa4b2f8d51c2814e702e4f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_language_drift_d6ffbf87_v1,
title = {language drift},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/language-drift/rdr_d6ffbf87f4fa4b2f8d51c2814e702e4f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}