In traditional RAG framework, the basic retrieval units are normally short. The common
retrievers like DPR normally work with 100-word Wikipedia paragraphs. Such a design …

Information seeking is an essential step for open-domain question answering to efficiently
gather evidence from a large corpus. Recently, iterative approaches have been proven to be …

The retrieval model is an indispensable component for real-world knowledge-intensive
tasks, eg, open-domain question answering (ODQA). As separate retrieval skills are …

We develop a unified system to answer directly from text open-domain questions that may
require a varying number of retrieval steps. We employ a single multi-task transformer model …

Existing approaches for open-domain question answering (QA) are typically designed for
questions that require either single-hop or multi-hop reasoning, which make strong …

Recently, large language models (LLMs) have gained much attention for the emergence of
human-comparable capabilities and huge potential. However, for open-domain implicit …

A key component of fact verification is thevevidence retrieval, often from multiple documents.
Recent approaches use dense representations and condition the retrieval of each document …

Multi-hop questions are associated with a series of justifications, and one needs to obtain
the answers by following the reasoning path (RP) that orders the justifications adequately …

We study the problem of Query Performance Prediction (QPP) for open-domain multi-hop
Question Answering (QA), where the task is to estimate the difficulty of evaluating a multi …

Currently, the most popular method for open-domain Question Answering (QA) adopts"
Retriever and Reader" pipeline, where the retriever extracts a list of candidate documents …