A RAG-augmented four-stage LLM pipeline ties a single-prompt baseline for first place in all three languages of a humor-generation shared task, and agentic scaffolding shows no clear quality gain on a 12-instance sample.
Peter McGraw and Caleb Warren
1 Pith paper cite this work, alongside 620 external citations. Polarity classification is still indexing.
1
Pith paper citing it
620
external citations · OpenAlex
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RAGthoven at SemEval-2026 Task 1: A Multi-Stage Pipeline Walks Into a Benchmark and Barely Clears the Bar
A RAG-augmented four-stage LLM pipeline ties a single-prompt baseline for first place in all three languages of a humor-generation shared task, and agentic scaffolding shows no clear quality gain on a 12-instance sample.