Commercial AI chatbots reach over 90% multiple-choice accuracy on recent news facts but lose 11-17% in free response and drop to 19-70% on subtle false-premise questions, with retrieval failures causing most errors and clear Anglophone bias.
MEGA : Multilingual Evaluation of Generative AI
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CL 5years
2026 5representative citing papers
LLMs can provide cost-effective annotation of credibility in Danish asylum texts but produce inconsistent errors that vary by model and prompt, requiring checks beyond single-model accuracy.
LLMs recover only ~20% of explicit pragmatic shifts under implicit cultural cues across five languages, responding mainly to linguistic structure rather than cultural associations as shown by Hindi-Urdu controls.
LLMs function as accurate semantic processors for conditionals but do not replicate the pragmatic inferences that define human reasoning.
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.
citing papers explorer
-
Evaluating Commercial AI Chatbots as News Intermediaries
Commercial AI chatbots reach over 90% multiple-choice accuracy on recent news facts but lose 11-17% in free response and drop to 19-70% on subtle false-premise questions, with retrieval failures causing most errors and clear Anglophone bias.
-
LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics
LLMs can provide cost-effective annotation of credibility in Danish asylum texts but produce inconsistent errors that vary by model and prompt, requiring checks beyond single-model accuracy.
-
Do LLMs Use Cultural Knowledge Without Being Told? A Multilingual Evaluation of Implicit Pragmatic Adaptation
LLMs recover only ~20% of explicit pragmatic shifts under implicit cultural cues across five languages, responding mainly to linguistic structure rather than cultural associations as shown by Hindi-Urdu controls.
-
Tracing the ongoing emergence of human-like reasoning in Large Language Models
LLMs function as accurate semantic processors for conditionals but do not replicate the pragmatic inferences that define human reasoning.
-
Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.