It's About Time: Incorporating Temporality in Retrieval Augmented Language Models

Publication Date

1-1-2025

Document Type

Conference Proceeding

Publication Title

Proceedings 2025 IEEE Conference on Artificial Intelligence Cai 2025

DOI

10.1109/CAI64502.2025.00019

First Page

75

Last Page

82

Abstract

In this paper, we propose and evaluate TempRALM, a temporally aware retrieval-augmented language model with few-shot learning capabilities, which considers both the semantic and temporal relevance of retrieved documents in relation to a given query, rather than relying on semantic similarity alone. Our approach demonstrates up to 7 4 % improvement in performance over the baseline state-of-the-art retrieval-augmented language model ATLAS, and 32% improvement over a state-of-the-art commercial large language model augmented with retrieval. TempRALM achieves these improvements without requiring model pre-training, document index replacement, or other computationally intensive operations. Additionally, we introduce and evaluate TablePedia, a novel automated method for generating ground truth data for retrieval-augmented language models and temporal question-answering.

Keywords

Information Retrieval, Retrieval, Temporality

Department

Computer Engineering

Link to Full Text

Share

COinS