5 papers
RE-TRIANGLE: Does TRIANGLE Enable Multimodal Alignment Beyond Cosine Similarity in Retrieval?
Arijit Ghosh, Aritra Bandyopadhyay, Chiranjeev Bindra +1
Multimodal alignment is critical for bridging the semantic gap in information retrieval. However, traditional pairwise strategies introduce a geometric blind spot: while they align…
LLM-based Listwise Reranking under the Effect of Positional Bias
Jingfen Qiao, Jin Huang, Xinyu Ma +4
LLM-based listwise passage reranking has attracted attention for its effectiveness in ranking candidate passages. However, these models suffer from positional bias, where passages…
Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction
Jingfen Qiao, Jia-Huei Ju, Xinyu Ma +2
Visual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly, bypassing the dependence on Optical Character Recogni…
Leveraging Decoder Architectures for Learned Sparse Retrieval
Jingfen Qiao, Thong Nguyen, Evangelos Kanoulas +1
Learned Sparse Retrieval (LSR) has traditionally focused on small-scale encoder-only transformer architectures. With the advent of large-scale pre-trained language models, their ca…
Agent-centric Information Access
Evangelos Kanoulas, Panagiotis Eustratiadis, Yongkang Li +5
As large language models (LLMs) become more specialized, we envision a future where millions of expert LLMs exist, each trained on proprietary data and excelling in specific domain…