@inproceedings{elshabrawy-etal-2025-enabling,
title = "Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning",
author = "Elshabrawy, Ahmed and
Huang, Yongxin and
Gurevych, Iryna and
Aji, Alham Fikri",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.465/",
doi = "10.18653/v1/2025.findings-naacl.465",
pages = "8302--8321",
ISBN = "979-8-89176-195-7",
abstract = "While Large Language Models (LLMs) exhibit remarkable capabilities in zero-shot and few-shot scenarios, they often require computationally prohibitive sizes. Conversely, smaller Masked Language Models (MLMs) like BERT and RoBERTa achieve state-of-the-art results through fine-tuning but struggle with extending to few-shot and zero-shot settings due to their architectural constraints. Hence, we propose Statement-Tuning, a technique that models discriminative tasks as a set of finite statements and trains an encoder model to discriminate between the potential statements to determine the label. We do Statement-Tuning on multiple tasks to enable cross-task generalization. Experimental results demonstrate that Statement-Tuning achieves competitive performance compared to state-of-the-art LLMs with significantly fewer parameters. Furthermore, we compare with previous encoder-based methodology and show that our method is more accurate and more robust to spurious patterns. Moreover, the study investigates the impact of several design choices on few-shot and zero-shot generalization, revealing that Statement-Tuning can achieve strong performance with modest training data and benefits from task and statement diversity for unseen task generalizability. We release all the code used to generate statement data, train and evaluate our Statement-Tuned models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elshabrawy-etal-2025-enabling">
<titleInfo>
<title>Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Elshabrawy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongxin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alham</namePart>
<namePart type="given">Fikri</namePart>
<namePart type="family">Aji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-195-7</identifier>
</relatedItem>
<abstract>While Large Language Models (LLMs) exhibit remarkable capabilities in zero-shot and few-shot scenarios, they often require computationally prohibitive sizes. Conversely, smaller Masked Language Models (MLMs) like BERT and RoBERTa achieve state-of-the-art results through fine-tuning but struggle with extending to few-shot and zero-shot settings due to their architectural constraints. Hence, we propose Statement-Tuning, a technique that models discriminative tasks as a set of finite statements and trains an encoder model to discriminate between the potential statements to determine the label. We do Statement-Tuning on multiple tasks to enable cross-task generalization. Experimental results demonstrate that Statement-Tuning achieves competitive performance compared to state-of-the-art LLMs with significantly fewer parameters. Furthermore, we compare with previous encoder-based methodology and show that our method is more accurate and more robust to spurious patterns. Moreover, the study investigates the impact of several design choices on few-shot and zero-shot generalization, revealing that Statement-Tuning can achieve strong performance with modest training data and benefits from task and statement diversity for unseen task generalizability. We release all the code used to generate statement data, train and evaluate our Statement-Tuned models.</abstract>
<identifier type="citekey">elshabrawy-etal-2025-enabling</identifier>
<identifier type="doi">10.18653/v1/2025.findings-naacl.465</identifier>
<location>
<url>https://aclanthology.org/2025.findings-naacl.465/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>8302</start>
<end>8321</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning
%A Elshabrawy, Ahmed
%A Huang, Yongxin
%A Gurevych, Iryna
%A Aji, Alham Fikri
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Findings of the Association for Computational Linguistics: NAACL 2025
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-195-7
%F elshabrawy-etal-2025-enabling
%X While Large Language Models (LLMs) exhibit remarkable capabilities in zero-shot and few-shot scenarios, they often require computationally prohibitive sizes. Conversely, smaller Masked Language Models (MLMs) like BERT and RoBERTa achieve state-of-the-art results through fine-tuning but struggle with extending to few-shot and zero-shot settings due to their architectural constraints. Hence, we propose Statement-Tuning, a technique that models discriminative tasks as a set of finite statements and trains an encoder model to discriminate between the potential statements to determine the label. We do Statement-Tuning on multiple tasks to enable cross-task generalization. Experimental results demonstrate that Statement-Tuning achieves competitive performance compared to state-of-the-art LLMs with significantly fewer parameters. Furthermore, we compare with previous encoder-based methodology and show that our method is more accurate and more robust to spurious patterns. Moreover, the study investigates the impact of several design choices on few-shot and zero-shot generalization, revealing that Statement-Tuning can achieve strong performance with modest training data and benefits from task and statement diversity for unseen task generalizability. We release all the code used to generate statement data, train and evaluate our Statement-Tuned models.
%R 10.18653/v1/2025.findings-naacl.465
%U https://aclanthology.org/2025.findings-naacl.465/
%U https://doi.org/10.18653/v1/2025.findings-naacl.465
%P 8302-8321
Markdown (Informal)
[Enabling Natural Zero-Shot Prompting on Encoder Models via Statement-Tuning](https://aclanthology.org/2025.findings-naacl.465/) (Elshabrawy et al., Findings 2025)
ACL