Greedy or not, here I come: Language production under vocabulary constraints in humans and resource-rational models
Quick Take
The study explores human language production under vocabulary constraints, comparing it to greedy and optimal sampling models.
Key Points
- Humans often exhibit greedy sampling behavior.
- Skilled individuals tend to backtrack and revise their language.
- Findings have implications for psycholinguistics and language impairments.
📖 Reader Mode
~2 min readAbstract:Communicating using only a limited vocabulary is a common but challenging cognitive phenomenon, requiring an ideal communicator to plan carefully to optimize for intelligibility while circumventing a constrained lexicon. In this work, we investigate how humans respond to a broad array of questions under variable vocabulary limitations, consisting of only 250 highly frequent words at the most restrictive. We provide theoretically motivated comparisons to greedy and globally optimal sampling algorithms using Sequential Monte Carlo inference with large language models. Humans generally resemble greedy sampling more than globally optimal sampling, though more skilled humans are more likely to backtrack and revise -- a non-greedy behavior. An observed human pattern of leaning on semantically light words in high-constraint settings falls out of both greedy and globally optimal sampling. We discuss the results and their broader implications for resource-rational cognition, psycholinguistics, L2 communication, and language impairments.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.15365 [cs.CL] |
| (or arXiv:2605.15365v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15365 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Thomas Clark [view email]
[v1]
Thu, 14 May 2026 19:45:02 UTC (175 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →arXiv cs.CL·Leyao Wang, Yanan He, Peng Chen, Asaf Yehudai, Yixin Liu, Rex Ying, Michal Shmueli-Scheuer, Arman Cohan
2d ago FeaturedOriginal
Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
AI Summary
The reliability of LLM judges for evaluating deep research agents is critically assessed using the REFLECT benchmark.