Using BM25 lexical retrieval to select prompt examples improves few-shot slot-filling F1 scores on ATIS, SNIPS, SLURP, and MEDIA compared to random or intent-only selection.
We present the datasets used, describe the chosen language model, detail the retrieval mechanisms em- ployed, and specify the baseline and comparison methods
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
background 1representative citing papers
citing papers explorer
-
Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning
Using BM25 lexical retrieval to select prompt examples improves few-shot slot-filling F1 scores on ATIS, SNIPS, SLURP, and MEDIA compared to random or intent-only selection.