mmPISA-bench evaluates two LLMs on 25 reasoning questions across 43 languages and finds effective multilingual reasoning at human levels with machine translations performing equivalently to human ones.
OECD Publishing, Paris (2023)
2 Pith papers cite this work, alongside 256 external citations. Polarity classification is still indexing.
2
Pith papers citing it
256
external citations · OpenAlex
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A neural model predicts future skill acquisition from snapshot data alone by using skill-set inclusions from cognitive diagnostic models to approximate unobserved learning paths.
citing papers explorer
-
mmPISA-bench: Do LLMs Reason Equally Well Across 43 Languages?
mmPISA-bench evaluates two LLMs on 25 reasoning questions across 43 languages and finds effective multilingual reasoning at human levels with machine translations performing equivalently to human ones.
-
Estimating Learners' Skill Acquisition Without Temporal Information
A neural model predicts future skill acquisition from snapshot data alone by using skill-set inclusions from cognitive diagnostic models to approximate unobserved learning paths.