In-context examples that encode a target distribution over document attributes can steer LLM rerankers toward fairness and diversity while roughly preserving relevance on four IR benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Modeling Ranking Properties with In-Context Learning
In-context examples that encode a target distribution over document attributes can steer LLM rerankers toward fairness and diversity while roughly preserving relevance on four IR benchmarks.