@inproceedings{afzal-etal-2025-da,
title = "{DA}-Pred: Performance Prediction for Text Summarization under Domain-Shift and Instruct-Tuning",
author = "Afzal, Anum and
Matthes, Florian and
Fabbri, Alexander",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.387/",
pages = "7632--7643",
ISBN = "979-8-89176-332-6",
abstract = "Large Language Models (LLMs) often don{'}t perform as expected under Domain Shift or after Instruct-tuning. A reliable indicator of LLM performance in these settings could assist in decision-making. We present a method that uses the known performance in high-resource domains and fine-tuning settings to predict performance in low-resource domains or base models, respectively. In our paper, we formulate the task of performance prediction, construct a dataset for it, and train regression models to predict the said change in performance. Our proposed methodology is lightweight and, in practice, can help researchers {\&} practitioners decide if resources should be allocated for data labeling and LLM Instruct-tuning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="afzal-etal-2025-da">
<titleInfo>
<title>DA-Pred: Performance Prediction for Text Summarization under Domain-Shift and Instruct-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anum</namePart>
<namePart type="family">Afzal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Matthes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fabbri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) often don’t perform as expected under Domain Shift or after Instruct-tuning. A reliable indicator of LLM performance in these settings could assist in decision-making. We present a method that uses the known performance in high-resource domains and fine-tuning settings to predict performance in low-resource domains or base models, respectively. In our paper, we formulate the task of performance prediction, construct a dataset for it, and train regression models to predict the said change in performance. Our proposed methodology is lightweight and, in practice, can help researchers & practitioners decide if resources should be allocated for data labeling and LLM Instruct-tuning.</abstract>
<identifier type="citekey">afzal-etal-2025-da</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.387/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>7632</start>
<end>7643</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DA-Pred: Performance Prediction for Text Summarization under Domain-Shift and Instruct-Tuning
%A Afzal, Anum
%A Matthes, Florian
%A Fabbri, Alexander
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F afzal-etal-2025-da
%X Large Language Models (LLMs) often don’t perform as expected under Domain Shift or after Instruct-tuning. A reliable indicator of LLM performance in these settings could assist in decision-making. We present a method that uses the known performance in high-resource domains and fine-tuning settings to predict performance in low-resource domains or base models, respectively. In our paper, we formulate the task of performance prediction, construct a dataset for it, and train regression models to predict the said change in performance. Our proposed methodology is lightweight and, in practice, can help researchers & practitioners decide if resources should be allocated for data labeling and LLM Instruct-tuning.
%U https://aclanthology.org/2025.emnlp-main.387/
%P 7632-7643
Markdown (Informal)
[DA-Pred: Performance Prediction for Text Summarization under Domain-Shift and Instruct-Tuning](https://aclanthology.org/2025.emnlp-main.387/) (Afzal et al., EMNLP 2025)
ACL