activity
20242026
collaborators

6 papers

cs.IR2026

Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies

Benjamin Clavié, Sean Lee, Aamir Shakir +1

We propose Latent Terms, a method revealing that models trained for dense retrieval, whether single- or multi-vector, learn representations that can trivially be decomposed into re…

cs.IR2026

ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking

Xianming Li, Aamir Shakir, Rui Huang +4

Reranking is fundamental to information retrieval and retrieval-augmented generation, with recent Large Language Models (LLMs) significantly advancing reranking quality. Most curre…

cs.IR2026

IncompeBench: A Permissively Licensed, Fine-Grained Benchmark for Music Information Retrieval

Benjamin Clavié, Atoof Shakir, Jonah Turner +3

Multimodal Information Retrieval has made significant progress in recent years, leveraging the increasingly strong multimodal abilities of deep pre-trained models to represent info…

cs.IR2025

Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report

Rikiya Takehi, Benjamin Clavié, Sean Lee +1

In this work, we introduce mxbai-edge-colbert-v0 models, at two different parameter counts: 17M and 32M. As part of our research, we conduct numerous experiments to improve retriev…

cs.IR2025

Simple Projection Variants Improve ColBERT Performance

Benjamin Clavié, Sean Lee, Rikiya Takehi +2

Multi-vector dense retrieval methods like ColBERT systematically use a single-layer linear projection to reduce the dimensionality of individual vectors. In this study, we explore…

cs.IR2024

BMX: Entropy-weighted Similarity and Semantic-enhanced Lexical Search

Xianming Li, Julius Lipp, Aamir Shakir +2

BM25, a widely-used lexical search algorithm, remains crucial in information retrieval despite the rise of pre-trained and large language models (PLMs/LLMs). However, it neglects q…