ARIS combines self-mixture-of-agents LLM decoding with a RoBERTa sequence tagger, consensus detection, confidence filtering, and LLM reflection to improve event extraction F1, but its headline SOTA claim is not supported on all datasets.
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
REJECT 1representative citing papers
citing papers explorer
-
Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction
ARIS combines self-mixture-of-agents LLM decoding with a RoBERTa sequence tagger, consensus detection, confidence filtering, and LLM reflection to improve event extraction F1, but its headline SOTA claim is not supported on all datasets.