@inproceedings{bae-etal-2025-salad,
title = "{SALAD}: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and {LLM}-Driven Augmented Data",
author = "Bae, Suyoung and
Choi, YunSeok and
Kim, Hyojun and
Lee, Jee-Hyong",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.634/",
doi = "10.18653/v1/2025.naacl-long.634",
pages = "12724--12738",
ISBN = "979-8-89176-189-6",
abstract = "In various natural language processing (NLP) tasks, fine-tuning Pre-trained Language Models (PLMs) often leads to the issue of spurious correlations, which negatively impacts performance, particularly when dealing with out-of-distribution data.To address this problem, we propose **SALAD** (**S**tructure **A**ware and **L**LM-driven **A**ugmented **D**ata), a novel approach designed to enhance model robustness and generalization by generating structure-aware and counterfactually augmented data for contrastive learning.Our method leverages a tagging-based approach to generate structure-aware positive samples and utilizes large language models (LLMs) to generate counterfactual negative samples with diverse sentence patterns. By applying contrastive learning, *SALAD* enables the model to focus on learning the structural relationships between key sentence components while minimizing reliance on spurious correlations.We validate our approach through experiments on three tasks: Sentiment Classification, Sexism Detection, and Natural Language Inference. The results demonstrate that *SALAD* not only improves model robustness and performance across different environments but also enhances generalization to out-of-distribution datasets and cross-domain scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bae-etal-2025-salad">
<titleInfo>
<title>SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suyoung</namePart>
<namePart type="family">Bae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">YunSeok</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyojun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jee-Hyong</namePart>
<namePart type="family">Lee</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>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</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">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>In various natural language processing (NLP) tasks, fine-tuning Pre-trained Language Models (PLMs) often leads to the issue of spurious correlations, which negatively impacts performance, particularly when dealing with out-of-distribution data.To address this problem, we propose **SALAD** (**S**tructure **A**ware and **L**LM-driven **A**ugmented **D**ata), a novel approach designed to enhance model robustness and generalization by generating structure-aware and counterfactually augmented data for contrastive learning.Our method leverages a tagging-based approach to generate structure-aware positive samples and utilizes large language models (LLMs) to generate counterfactual negative samples with diverse sentence patterns. By applying contrastive learning, *SALAD* enables the model to focus on learning the structural relationships between key sentence components while minimizing reliance on spurious correlations.We validate our approach through experiments on three tasks: Sentiment Classification, Sexism Detection, and Natural Language Inference. The results demonstrate that *SALAD* not only improves model robustness and performance across different environments but also enhances generalization to out-of-distribution datasets and cross-domain scenarios.</abstract>
<identifier type="citekey">bae-etal-2025-salad</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.634</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.634/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>12724</start>
<end>12738</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data
%A Bae, Suyoung
%A Choi, YunSeok
%A Kim, Hyojun
%A Lee, Jee-Hyong
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F bae-etal-2025-salad
%X In various natural language processing (NLP) tasks, fine-tuning Pre-trained Language Models (PLMs) often leads to the issue of spurious correlations, which negatively impacts performance, particularly when dealing with out-of-distribution data.To address this problem, we propose **SALAD** (**S**tructure **A**ware and **L**LM-driven **A**ugmented **D**ata), a novel approach designed to enhance model robustness and generalization by generating structure-aware and counterfactually augmented data for contrastive learning.Our method leverages a tagging-based approach to generate structure-aware positive samples and utilizes large language models (LLMs) to generate counterfactual negative samples with diverse sentence patterns. By applying contrastive learning, *SALAD* enables the model to focus on learning the structural relationships between key sentence components while minimizing reliance on spurious correlations.We validate our approach through experiments on three tasks: Sentiment Classification, Sexism Detection, and Natural Language Inference. The results demonstrate that *SALAD* not only improves model robustness and performance across different environments but also enhances generalization to out-of-distribution datasets and cross-domain scenarios.
%R 10.18653/v1/2025.naacl-long.634
%U https://aclanthology.org/2025.naacl-long.634/
%U https://doi.org/10.18653/v1/2025.naacl-long.634
%P 12724-12738
Markdown (Informal)
[SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data](https://aclanthology.org/2025.naacl-long.634/) (Bae et al., NAACL 2025)
ACL