Language and Experience: A Computational Model of Social Learning in Complex Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908838569967616 |
|---|---|
| author | Colas, Cédric Mills, Tracey Prystawski, Ben Tessler, Michael Henry Goodman, Noah Andreas, Jacob Tenenbaum, Joshua |
| author_facet | Colas, Cédric Mills, Tracey Prystawski, Ben Tessler, Michael Henry Goodman, Noah Andreas, Jacob Tenenbaum, Joshua |
| contents | The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI systems? We present a computational framework that models social learning as joint probabilistic inference over structured, executable world models given sensorimotor and linguistic data. We make this possible by turning a pretrained language model into a probabilistic model of how humans share advice conditioned on their beliefs, allowing our agents both to generate advice for others and to interpret linguistic input as evidence during Bayesian inference. Using behavioral experiments and simulations across 10 video games, we show how linguistic guidance can shape exploration and accelerate learning by reducing risky interactions and speeding up key discoveries in both humans and models. We further explore how knowledge can accumulate across generations through iterated learning experiments and demonstrate successful knowledge transfer between humans and models -- revealing how structured, language-compatible representations might enable human-machine collaborative learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00074 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Language and Experience: A Computational Model of Social Learning in Complex Tasks Colas, Cédric Mills, Tracey Prystawski, Ben Tessler, Michael Henry Goodman, Noah Andreas, Jacob Tenenbaum, Joshua Artificial Intelligence Computation and Language Machine Learning The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people integrate these two sources of knowledge, and how might AI systems? We present a computational framework that models social learning as joint probabilistic inference over structured, executable world models given sensorimotor and linguistic data. We make this possible by turning a pretrained language model into a probabilistic model of how humans share advice conditioned on their beliefs, allowing our agents both to generate advice for others and to interpret linguistic input as evidence during Bayesian inference. Using behavioral experiments and simulations across 10 video games, we show how linguistic guidance can shape exploration and accelerate learning by reducing risky interactions and speeding up key discoveries in both humans and models. We further explore how knowledge can accumulate across generations through iterated learning experiments and demonstrate successful knowledge transfer between humans and models -- revealing how structured, language-compatible representations might enable human-machine collaborative learning. |
| title | Language and Experience: A Computational Model of Social Learning in Complex Tasks |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2509.00074 |