11 papers
Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning
Jiahan Chen, Da Li, Hengran Zhang +6
Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classi…
An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs
Hengran Zhang, Keping Bi, Jiafeng Guo +1
Relevance and utility are two frequently used measures to evaluate the effectiveness of an information retrieval (IR) system. Relevance emphasizes the aboutness of a result to a qu…
Beyond Relevance: Utility-Centric Retrieval in the LLM Era
Hengran Zhang, Minghao Tang, Keping Bi +1
Information retrieval systems have traditionally optimized for topical relevance-the degree to which retrieved documents match a query. However, relevance only approximates a deepe…
Training Dense Retrievers with Multiple Positive Passages
Benben Wang, Minghao Tang, Hengran Zhang +2
Modern knowledge-intensive systems, such as retrieval-augmented generation (RAG), rely on effective retrievers to establish the performance ceiling for downstream modules. However,…
Bagging-Based Model Merging for Robust General Text Embeddings
Hengran Zhang, Keping Bi, Jiafeng Guo +4
General-purpose text embedding models underpin a wide range of NLP and information retrieval applications, and are typically trained on large-scale multi-task corpora to encourage…
LLM-Specific Utility for Retrieval-Augmented Generation
Hengran Zhang, Keping Bi, Jiafeng Guo +4
Retrieval-augmented generation (RAG) is typically optimized for topical relevance, yet its success ultimately depends on whether retrieved passages are useful for a large language…