LLMs exhibit mid-layer representation advantage for recommendations; MARC compresses representations modularly to reduce costs while improving performance, as shown in a large-scale online advertising deployment.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 2roles
background 1polarities
background 1representative citing papers
R2MED is the first benchmark for reasoning-driven medical retrieval, where even top models reach only 41.4 nDCG@10 on queries requiring inference beyond lexical or semantic overlap.
citing papers explorer
-
Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations
LLMs exhibit mid-layer representation advantage for recommendations; MARC compresses representations modularly to reduce costs while improving performance, as shown in a large-scale online advertising deployment.
-
R2MED: A Benchmark for Reasoning-Driven Medical Retrieval
R2MED is the first benchmark for reasoning-driven medical retrieval, where even top models reach only 41.4 nDCG@10 on queries requiring inference beyond lexical or semantic overlap.