English prompts produce better LLM-designed reward functions for RMABs than Hindi, Tamil, or Tulu prompts, and complex prompts worsen performance and fairness across languages.
J.; Loftus, J.; Russell, C.; and Silva, R
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multilinguality in LLM-Designed Reward Functions for Restless Bandits: Effects on Task Performance and Fairness
English prompts produce better LLM-designed reward functions for RMABs than Hindi, Tamil, or Tulu prompts, and complex prompts worsen performance and fairness across languages.