Two-Step Question Retrieval for Open-Domain QA

[PDF] arxiv.org

A survey for efficient open domain question answering

Q Zhang, S Chen, D Xu, Q Cao, X Chen, T Cohn… - arXiv preprint arXiv …, 2022 - arxiv.org
Open domain question answering (ODQA) is a longstanding task aimed at answering factual
questions from a large knowledge corpus without any explicit evidence in natural language …
被引用次数：44 相关文章 所有 5 个版本
[PDF] arxiv.org

When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively

T Labruna, JA Campos, G Azkune - arXiv preprint arXiv:2404.19705, 2024 - arxiv.org
In this paper, we demonstrate how Large Language Models (LLMs) can effectively learn to
use an off-the-shelf information retrieval (IR) system specifically when additional context is …
被引用次数：5 相关文章 所有 2 个版本

A Principled Decomposition of Pointwise Mutual Information for Intention Template Discovery

D Ma, K Chen-Chuan Chang, Y Chen, X Lv… - Proceedings of the 32nd …, 2023 - dl.acm.org
With the rise of Artificial Intelligence (AI), question answering systems have become
common for users to interact with computers, eg, ChatGPT and Siri. These systems require a …
被引用次数：1 相关文章 所有 2 个版本
[PDF] arxiv.org

Quadro: Dataset and models for question-answer database retrieval

S Campese, I Lauriola, A Moschitti - arXiv preprint arXiv:2304.01003, 2023 - arxiv.org
An effective paradigm for building Automated Question Answering systems is the re-use of
previously answered questions, eg, for FAQs or forum applications. Given a database (DB) …
被引用次数：5 相关文章 所有 5 个版本