Analysis of Language Change in Collaborative Instruction Following
Not on the map. Why?
Abstract (arXiv)
We analyze language change over time in a collaborative, goal-oriented instructional task, where utility-maximizing participants form conventions and increase their expertise. Prior work studied such scenarios mostly in the context of reference games, and consistently found that language complexity is reduced along multiple dimensions, such as utterance length, as conventions are formed. In contrast, we find that, given the ability to increase instruction utility, instructors increase language complexity along these previously studied dimensions to better collaborate with increasingly skilled instruction followers.
Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 9 of its 21 references that are in the map. First posted on arXiv 9 Sep 2021.
Builds on
9 of 21 references.
References · 9
- 2019Executing Instructions in Situated Collaborative Interactionscited by 68
- 2017Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddingscited by 59
- 2017Colors in Context: A Pragmatic Neural Model for Grounded Language Understandingcited by 57
- 2019The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialoguecited by 46
- 2019A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Contextcited by 35
- 2019Characterizing the dynamics of learning in repeated reference gamescited by 34
- 2017Naturalizing a Programming Language via Interactive Learningcited by 20
- 2020Generalizing meanings from partners to populations: Hierarchical inference supports convention formation on networkscited by 4
- 2018Precise but Natural Specification for Robot Taskscited by 1
Built on by
Citing papers per year: 2022: 3; 2023: 1; 2024: 4; 2025: 0; 2026: 1.
9 papers.
- 2022Continual Learning for Instruction Following from Realtime Feedbackcited by 21
- 2024Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMscited by 18
- 2022Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approachescited by 12
- 2022MUG: Interactive Multimodal Grounding on User Interfacescited by 9
- 2024CoGen: Learning from Feedback with Coupled Comprehension and Generationcited by 7
- 2024Retrospective Learning from Interactionscited by 6
- 2024Situated Instruction Followingcited by 3
- 2023CB2: Collaborative Natural Language Interaction Research Platformcited by 1
- 2026Online library learning in human visual puzzle solvingcited by 1
- 2026Online library learning in human visual puzzle solving24 Mar 2026
- 2024Retrospective Learning from Interactions17 Oct 2024
- 2024CoGen: Learning from Feedback with Coupled Comprehension and Generation28 Aug 2024
- 2024Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs2 Aug 2024
- 2024Situated Instruction Following15 Jul 2024
- 2023CB2: Collaborative Natural Language Interaction Research Platform14 Mar 2023
- 2022Continual Learning for Instruction Following from Realtime Feedback19 Dec 2022
- 2022Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches15 Nov 2022
- 2022MUG: Interactive Multimodal Grounding on User Interfaces29 Sep 2022