1 citations · 2 across the 8 of their papers we have counts for
5 papers · 1 filter
Improving Long-Context Retrieval with Multi-Prefix Embedding
Zhenglin Yu, Xueguang Ma, Shengyao Zhuang +4
Long-context retrieval exposes a tension: single-vector embeddings lose fine-grained detail, while token-level multi-vector methods incur prohibitive storage. We propose Multi-Pref…
Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh +1
We investigate improving the retrieval effectiveness of embedding models through the lens of corpus-specific fine-tuning. Prior work has shown that fine-tuning with queries generat…
Teaching Dense Retrieval Models to Specialize with Listwise Distillation and LLM Data Augmentation
Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh +1
While the current state-of-the-art dense retrieval models exhibit strong out-of-domain generalization, they might fail to capture nuanced domain-specific knowledge. In principle, f…
Illusions of Relevance: Arbitrary Content Injection Attacks Deceive Retrievers, Rerankers, and LLM Judges
Manveer Singh Tamber, Jimmy Lin
This work considers a black-box threat model in which adversaries attempt to propagate arbitrary non-relevant content in search. We show that retrievers, rerankers, and LLM relevan…
Can't Hide Behind the API: Stealing Black-Box Commercial Embedding Models
Manveer Singh Tamber, Jasper Xian, Jimmy Lin
Embedding models that generate dense vector representations of text are widely used and hold significant commercial value. Companies such as OpenAI and Cohere offer proprietary emb…