A single LLM rewrite of skill descriptions using false positive and negative cases matches manual optimization performance in production, with most other pipeline components adding little value.
Investigating the Effect of Natural Language Explanations on Out-of-Distribution Generalization in Few-shot NLI
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization
A single LLM rewrite of skill descriptions using false positive and negative cases matches manual optimization performance in production, with most other pipeline components adding little value.