@inproceedings{degenaro-etal-2025-fortify,
title = "{FORTIFY}: Generative Model Fine-tuning with {ORPO} for {R}e{T}rieval Expansion of {I}n{F}ormal {N}ois{Y} Text",
author = "DeGenaro, Dan and
Yang, Eugene and
Etter, David and
Carpenter, Cameron and
Sanders, Kate and
Martin, Alexander and
Murray, Kenton and
Kriz, Reno",
editor = "Kriz, Reno and
Murray, Kenton",
booktitle = "Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.magmar-1.13/",
doi = "10.18653/v1/2025.magmar-1.13",
pages = "100--115",
ISBN = "979-8-89176-280-0",
abstract = "Despite recent advancements in neural retrieval, representing text fragments or phrases with proper contextualized embeddings is still challenging. Particularly in video retrieval, where documents are text extracted through OCR from the frames or ASR from audio tracks, the textual content is rarely complete sentences but only a bag of phrases. In this work, we propose FORTIFY, a generative model fine-tuning approach for noisy document rewriting and summarization, to improve the downstream retrieval effectiveness. By experimenting on MultiVENT 2.0, an informational video retrieval benchmark, we show Llama fine-tuned with FORTIFY provides an effective document expansion, leading to a 30{\%} improvement over prompting an out-of-box Llama model on nDCG@10. Zero-shot transferring the model tailored for MultiVENT 2.0 to two out-of-distribution datasets still demonstrates competitive retrieval effectiveness to other document preprocessing alternatives."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="degenaro-etal-2025-fortify">
<titleInfo>
<title>FORTIFY: Generative Model Fine-tuning with ORPO for ReTrieval Expansion of InFormal NoisY Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">DeGenaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Etter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cameron</namePart>
<namePart type="family">Carpenter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kate</namePart>
<namePart type="family">Sanders</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenton</namePart>
<namePart type="family">Murray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reno</namePart>
<namePart type="family">Kriz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reno</namePart>
<namePart type="family">Kriz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenton</namePart>
<namePart type="family">Murray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-280-0</identifier>
</relatedItem>
<abstract>Despite recent advancements in neural retrieval, representing text fragments or phrases with proper contextualized embeddings is still challenging. Particularly in video retrieval, where documents are text extracted through OCR from the frames or ASR from audio tracks, the textual content is rarely complete sentences but only a bag of phrases. In this work, we propose FORTIFY, a generative model fine-tuning approach for noisy document rewriting and summarization, to improve the downstream retrieval effectiveness. By experimenting on MultiVENT 2.0, an informational video retrieval benchmark, we show Llama fine-tuned with FORTIFY provides an effective document expansion, leading to a 30% improvement over prompting an out-of-box Llama model on nDCG@10. Zero-shot transferring the model tailored for MultiVENT 2.0 to two out-of-distribution datasets still demonstrates competitive retrieval effectiveness to other document preprocessing alternatives.</abstract>
<identifier type="citekey">degenaro-etal-2025-fortify</identifier>
<identifier type="doi">10.18653/v1/2025.magmar-1.13</identifier>
<location>
<url>https://aclanthology.org/2025.magmar-1.13/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>100</start>
<end>115</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FORTIFY: Generative Model Fine-tuning with ORPO for ReTrieval Expansion of InFormal NoisY Text
%A DeGenaro, Dan
%A Yang, Eugene
%A Etter, David
%A Carpenter, Cameron
%A Sanders, Kate
%A Martin, Alexander
%A Murray, Kenton
%A Kriz, Reno
%Y Kriz, Reno
%Y Murray, Kenton
%S Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-280-0
%F degenaro-etal-2025-fortify
%X Despite recent advancements in neural retrieval, representing text fragments or phrases with proper contextualized embeddings is still challenging. Particularly in video retrieval, where documents are text extracted through OCR from the frames or ASR from audio tracks, the textual content is rarely complete sentences but only a bag of phrases. In this work, we propose FORTIFY, a generative model fine-tuning approach for noisy document rewriting and summarization, to improve the downstream retrieval effectiveness. By experimenting on MultiVENT 2.0, an informational video retrieval benchmark, we show Llama fine-tuned with FORTIFY provides an effective document expansion, leading to a 30% improvement over prompting an out-of-box Llama model on nDCG@10. Zero-shot transferring the model tailored for MultiVENT 2.0 to two out-of-distribution datasets still demonstrates competitive retrieval effectiveness to other document preprocessing alternatives.
%R 10.18653/v1/2025.magmar-1.13
%U https://aclanthology.org/2025.magmar-1.13/
%U https://doi.org/10.18653/v1/2025.magmar-1.13
%P 100-115
Markdown (Informal)
[FORTIFY: Generative Model Fine-tuning with ORPO for ReTrieval Expansion of InFormal NoisY Text](https://aclanthology.org/2025.magmar-1.13/) (DeGenaro et al., MAGMaR 2025)
ACL
- Dan DeGenaro, Eugene Yang, David Etter, Cameron Carpenter, Kate Sanders, Alexander Martin, Kenton Murray, and Reno Kriz. 2025. FORTIFY: Generative Model Fine-tuning with ORPO for ReTrieval Expansion of InFormal NoisY Text. In Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025), pages 100–115, Vienna, Austria. Association for Computational Linguistics.