A hierarchical multi-agent LLM framework, in which a coordinating analyzer synthesizes query and item specialist outputs, beats flat, staged, and ensemble LLM relevance judges on five content search datasets.
LLMs can be Fooled into Labelling a Document as Relevant: best caf
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.MA 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
HIERA: Hierarchical Multi-Agent Relevance Assessment for Content Discovery Systems
A hierarchical multi-agent LLM framework, in which a coordinating analyzer synthesizes query and item specialist outputs, beats flat, staged, and ensemble LLM relevance judges on five content search datasets.