Investigating Task Arithmetic for Zero-Shot Information Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Braga, Marco, Kasela, Pranav, Raganato, Alessandro, Pasi, Gabriella
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915269096505344
author Braga, Marco
Kasela, Pranav
Raganato, Alessandro
Pasi, Gabriella
author_facet Braga, Marco
Kasela, Pranav
Raganato, Alessandro
Pasi, Gabriella
contents Large Language Models (LLMs) have shown impressive zero-shot performance across a variety of Natural Language Processing tasks, including document re-ranking. However, their effectiveness degrades on unseen tasks and domains, largely due to shifts in vocabulary and word distributions. In this paper, we investigate Task Arithmetic, a technique that combines the weights of LLMs pre-trained on different tasks or domains via simple mathematical operations, such as addition or subtraction, to adapt retrieval models without requiring additional fine-tuning. Our method is able to synthesize diverse tasks and domain knowledge into a single model, enabling effective zero-shot adaptation in different retrieval contexts. Extensive experiments on publicly available scientific, biomedical, and multilingual datasets show that our method improves state-of-the-art re-ranking performance by up to 18% in NDCG@10 and 15% in P@10. In addition to these empirical gains, our analysis provides insights into the strengths and limitations of Task Arithmetic as a practical strategy for zero-shot learning and model adaptation. We make our code publicly available at https://github.com/DetectiveMB/Task-Arithmetic-for-ZS-IR.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00649
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Investigating Task Arithmetic for Zero-Shot Information Retrieval
Braga, Marco
Kasela, Pranav
Raganato, Alessandro
Pasi, Gabriella
Information Retrieval
Computation and Language
Machine Learning
Large Language Models (LLMs) have shown impressive zero-shot performance across a variety of Natural Language Processing tasks, including document re-ranking. However, their effectiveness degrades on unseen tasks and domains, largely due to shifts in vocabulary and word distributions. In this paper, we investigate Task Arithmetic, a technique that combines the weights of LLMs pre-trained on different tasks or domains via simple mathematical operations, such as addition or subtraction, to adapt retrieval models without requiring additional fine-tuning. Our method is able to synthesize diverse tasks and domain knowledge into a single model, enabling effective zero-shot adaptation in different retrieval contexts. Extensive experiments on publicly available scientific, biomedical, and multilingual datasets show that our method improves state-of-the-art re-ranking performance by up to 18% in NDCG@10 and 15% in P@10. In addition to these empirical gains, our analysis provides insights into the strengths and limitations of Task Arithmetic as a practical strategy for zero-shot learning and model adaptation. We make our code publicly available at https://github.com/DetectiveMB/Task-Arithmetic-for-ZS-IR.
title Investigating Task Arithmetic for Zero-Shot Information Retrieval
topic Information Retrieval
Computation and Language
Machine Learning
url https://arxiv.org/abs/2505.00649