LLM-enhanced retrieval systems show large effectiveness gains on TREC benchmarks, yet adapted contamination checks indicate some gains may arise from memorization rather than methodological progress.
Armstrong, Alistair Moffat, William Webber, and Justin Zobel
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2verdicts
UNVERDICTED 2representative citing papers
An unsupervised character-level CNN encoder with attention-based RNN decoder, trained on Clueweb09 anchor phrases, generates query reformulations that improve retrieval on TREC collections.
citing papers explorer
-
The LLM Effect on IR Benchmarks: A Meta-Analysis of Effectiveness, Baselines, and Contamination
LLM-enhanced retrieval systems show large effectiveness gains on TREC benchmarks, yet adapted contamination checks indicate some gains may arise from memorization rather than methodological progress.
-
Learning to Reformulate the Queries on the WEB
An unsupervised character-level CNN encoder with attention-based RNN decoder, trained on Clueweb09 anchor phrases, generates query reformulations that improve retrieval on TREC collections.