6 papers
AttentionRetriever: Attention Layers are Secretly Long Document Retrievers
David Jiahao Fu, Lam Thanh Do, Jiayu Li +1
Retrieval augmented generation (RAG) has been widely adopted to help Large Language Models (LLMs) to process tasks involving long documents. However, existing retrieval models are…
IRB: Automated Generation of Robust Factuality Benchmarks
Lam Thanh Do, Bhagyashree Taleka, Hozaifa Ammar Bhutta +3
Static benchmarks for RAG systems often suffer from rapid saturation and require significant manual effort to maintain robustness. To address this, we present IRB, a framework for…
CASPER: Concept-integrated Sparse Representation for Scientific Retrieval
Lam Thanh Do, Linh Van Nguyen, Jiayu Li +2
Identifying relevant research concepts is crucial for effective scientific search. However, primary sparse retrieval methods often lack concept-aware representations. To address th…
ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation
Lam Thanh Do, Aaditya Bodke, Pritom Saha Akash +1
Unsupervised keyphrase prediction has gained growing interest in recent years. However, existing methods typically rely on heuristically defined importance scores, which may lead t…
Unsupervised Open-domain Keyphrase Generation
Lam Thanh Do, Pritom Saha Akash, Kevin Chen-Chuan Chang
In this work, we study the problem of unsupervised open-domain keyphrase generation, where the objective is a keyphrase generation model that can be built without using human-label…
MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization Problem
Hieu Trong Phung, Anh Tuan Vu, Tung Dinh Nguyen +4
In this work, we study a new image annotation task named Extractive Tags Summarization (ETS). The goal is to extract important tags from the context lying in an image and its corre…