RESS, which prompts LLMs from six language-learning aspects and ensembles the results, improves Chinese buzzword definition generation over baselines, while the benchmark shows LLMs over-rely on prior exposure to buzzwords.
Title resolution pending
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
-
Can Large Language Models Understand Internet Buzzwords Through User-Generated Content
RESS, which prompts LLMs from six language-learning aspects and ensembles the results, improves Chinese buzzword definition generation over baselines, while the benchmark shows LLMs over-rely on prior exposure to buzzwords.