Fine-tuning LLMs with retrieval-augmented prompts and self-correction yields SOTA SRL scores on three benchmarks, but the gains rest on a near-oracle predicate retrieval agent.
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
-
LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models
Fine-tuning LLMs with retrieval-augmented prompts and self-correction yields SOTA SRL scores on three benchmarks, but the gains rest on a near-oracle predicate retrieval agent.