English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this work, we investigate the capacity of language models to generateexplicit, interpretable, and interactive world models of scientific andcommon-sense reasoning tasks. We operationalize this as a task of generatingtext games, expressed as hundreds of lines of Python code. To facilitate thistask, we introduce ByteSized32 (Code: github.com/cognitiveailab/BYTESIZED32), acorpus of 32 reasoning-focused text games totaling 20k lines of Python code. Weempirically demonstrate that GPT-4 can use these games as templates forsingle-shot in-context learning, successfully producing runnable games onunseen topics in 28% of cases. When allowed to self-reflect on program errors,game runnability substantially increases to 57%. While evaluating simulationfidelity is labor-intensive, we introduce a suite of automated metrics toassess game fidelity, technical validity, adherence to task specifications, andwinnability, showing a high degree of agreement with expert human ratings. Wepose this as a challenge task to spur further development at the juncture ofworld modeling and code generation.

ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games