Effect of Model Merging in Domain-Specific Ad-hoc Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sasaki, Taiga, Yamamoto, Takehiro, Ohshima, Hiroaki, Fujita, Sumio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915516157788160
author Sasaki, Taiga
Yamamoto, Takehiro
Ohshima, Hiroaki
Fujita, Sumio
author_facet Sasaki, Taiga
Yamamoto, Takehiro
Ohshima, Hiroaki
Fujita, Sumio
contents In this study, we evaluate the effect of model merging in ad-hoc retrieval tasks. Model merging is a technique that combines the diverse characteristics of multiple models. We hypothesized that applying model merging to domain-specific ad-hoc retrieval tasks could improve retrieval effectiveness. To verify this hypothesis, we merged the weights of a source retrieval model and a domain-specific (non-retrieval) model using a linear interpolation approach. A key advantage of our approach is that it requires no additional fine-tuning of the models. We conducted two experiments each in the medical and Japanese domains. The first compared the merged model with the source retrieval model, and the second compared it with a LoRA fine-tuned model under both full and limited data settings for model construction. The experimental results indicate that model merging has the potential to produce more effective domain-specific retrieval models than the source retrieval model, and may serve as a practical alternative to LoRA fine-tuning, particularly when only a limited amount of data is available.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21966
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Effect of Model Merging in Domain-Specific Ad-hoc Retrieval
Sasaki, Taiga
Yamamoto, Takehiro
Ohshima, Hiroaki
Fujita, Sumio
Information Retrieval
In this study, we evaluate the effect of model merging in ad-hoc retrieval tasks. Model merging is a technique that combines the diverse characteristics of multiple models. We hypothesized that applying model merging to domain-specific ad-hoc retrieval tasks could improve retrieval effectiveness. To verify this hypothesis, we merged the weights of a source retrieval model and a domain-specific (non-retrieval) model using a linear interpolation approach. A key advantage of our approach is that it requires no additional fine-tuning of the models. We conducted two experiments each in the medical and Japanese domains. The first compared the merged model with the source retrieval model, and the second compared it with a LoRA fine-tuned model under both full and limited data settings for model construction. The experimental results indicate that model merging has the potential to produce more effective domain-specific retrieval models than the source retrieval model, and may serve as a practical alternative to LoRA fine-tuning, particularly when only a limited amount of data is available.
title Effect of Model Merging in Domain-Specific Ad-hoc Retrieval
topic Information Retrieval
url https://arxiv.org/abs/2509.21966