11 papers · 1 filter
The Powerless Noise: How Experimental Settings Shape the Reported Power of Noise
Michał Mazuryk, Fleur Dolmans, Louis Gehringer +3
Recent work has suggested that adding irrelevant documents to the input of retrieval-augmented generation (RAG) systems can improve question-answering performance, a phenomenon ref…
Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
Jia-Huei Ju, Eugene Yang, Trevor Adriaanse +2
Long-form Retrieval-Augmented Generation (RAG) brings the challenge of coverage-based ranking, because ranking methods must ensure the inclusion of comprehensive relevant nuggets (…
LANCER: LLM Reranking for Nugget Coverage
Jia-Huei Ju, François G. Landry, Eugene Yang +2
Unlike short-form retrieval-augmented generation (RAG), such as factoid question answering, long-form RAG requires retrieval to provide documents covering a wide range of relevant…
To Case or Not to Case: An Empirical Study in Learned Sparse Retrieval
Emmanouil Georgios Lionis, Jia-Huei Ju, Angelos Nalmpantis +3
Learned Sparse Retrieval (LSR) methods construct sparse lexical representations of queries and documents that can be efficiently searched using inverted indexes. Existing LSR appro…
Incorporating Q&A Nuggets into Retrieval-Augmented Generation
Laura Dietz, Bryan Li, Gabrielle Liu +5
RAGE systems integrate ideas from automatic evaluation (E) into Retrieval-augmented Generation (RAG). As one such example, we present Crucible, a Nugget-Augmented Generation System…
Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector
Thong Nguyen, Yibin Lei, Jia-Huei Ju +2
Learned Sparse Retrieval (LSR) combines the efficiency of bi-encoders with the transparency of lexical matching, but existing approaches struggle to scale beyond English. We introd…
Augmenting Researchy Questions with Sub-question Judgments
Jia-Huei Ju, Eugene Yang, Trevor Adriaanse +1
The Researchy Questions dataset provides about 100k question queries with complex information needs that require retrieving information about several aspects of a topic. Each query…
SERVAL: Surprisingly Effective Zero-Shot Visual Document Retrieval Powered by Large Vision and Language Models
Thong Nguyen, Yibin Lei, Jia-Huei Ju +1
Visual Document Retrieval (VDR) typically operates as text-to-image retrieval using specialized bi-encoders trained to directly embed document images. We revisit a zero-shot genera…
Controlled Retrieval-augmented Context Evaluation for Long-form RAG
Jia-Huei Ju, Suzan Verberne, Maarten de Rijke +1
Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval mod…
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…
On the Reproducibility of Learned Sparse Retrieval Adaptations for Long Documents
Emmanouil Georgios Lionis, Jia-Huei Ju
Document retrieval is one of the most challenging tasks in Information Retrieval. It requires handling longer contexts, often resulting in higher query latency and increased comput…