Saved in:
Bibliographic Details
Main Authors: Liu, Weisi, Han, Guangzeng, Huang, Xiaolei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22098
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914503590936576
author Liu, Weisi
Han, Guangzeng
Huang, Xiaolei
author_facet Liu, Weisi
Han, Guangzeng
Huang, Xiaolei
contents Time introduces fundamental challenges in model development and deployment: models are usually trained on historical data while deployed on future data where semantic distributions and domain knowledge may evolve. Unfortunately, existing studies either overlook temporal shifts or hardly capture rich shifting patterns of both semantic and knowledge. We develop Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation (KARITA) to capture diverse temporal shifts (e.g., uncertainty and feature shift), construct and integrate rich knowledge sources (e.g., medical ontology like MeSH), and leverage shifting insights for selecting-retrieval augmented learning. We evaluate KARITA on classification tasks across multiple domains, clinical, legal, and scientific corpora, demonstrating consistent improvements across multiple domains with temporal adaptation. Our results show that knowledge integration can be more critical and effective in temporal augmentation and learning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22098
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation
Liu, Weisi
Han, Guangzeng
Huang, Xiaolei
Computation and Language
Time introduces fundamental challenges in model development and deployment: models are usually trained on historical data while deployed on future data where semantic distributions and domain knowledge may evolve. Unfortunately, existing studies either overlook temporal shifts or hardly capture rich shifting patterns of both semantic and knowledge. We develop Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation (KARITA) to capture diverse temporal shifts (e.g., uncertainty and feature shift), construct and integrate rich knowledge sources (e.g., medical ontology like MeSH), and leverage shifting insights for selecting-retrieval augmented learning. We evaluate KARITA on classification tasks across multiple domains, clinical, legal, and scientific corpora, demonstrating consistent improvements across multiple domains with temporal adaptation. Our results show that knowledge integration can be more critical and effective in temporal augmentation and learning.
title Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation
topic Computation and Language
url https://arxiv.org/abs/2604.22098