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.
Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Existing cross-encoder models can be categorized as pointwise, pairwise, or listwise. Pairwise and listwise models allow passage interactions, which typically makes them more effective than pointwise models but less efficient and less robust to input passage order permutations. To enable efficient permutation-invariant passage interactions during re-ranking, we propose a new cross-encoder architecture with inter-passage attention: the Set-Encoder. In experiments on TREC Deep Learning and TIREx, the Set-Encoder is as effective as state-of-the-art listwise models while being more efficient and invariant to input passage order permutations. Compared to pointwise models, the Set-Encoder is particularly more effective when considering inter-passage information, such as novelty, and retains its advantageous properties compared to other listwise models. Our code is publicly available at https://github.com/webis-de/ECIR-25.
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.