The paper explores different strategies for integrating retrieved passages with large language models (LLMs) to enhance open-domain question answering. The authors first examine the limitations of a commonly used concatenation approach, which often results in "unknown" outputs even when the correct document is among the top-k retrieved passages.
To address this issue, the authors explore four alternative strategies:
Two single-round methods that utilize chain-of-thought reasoning:
Two multi-round approaches that incorporate feedback loops:
Through comprehensive experiments on three open-domain question-answering datasets (NQ, TriviaQA, and SQuAD), the authors demonstrate that their multi-round approaches outperform the traditional concatenation approach, achieving over a 10% improvement in answer exact match (EM).
The paper also provides insights into the optimal placement of the gold passage within the top-k retrieved passages, the effect of different decoding strategies, and the token usage analysis of the proposed methods.
To Another Language
from source content
arxiv.org
Principais Insights Extraídos De
by Ye Liu,Semih... às arxiv.org 04-09-2024
https://arxiv.org/pdf/2308.12574.pdfPerguntas Mais Profundas