Challenge: Paraphrase identification models have been shown to be vulnerable and lack robustness in tasks such as text classification and natural language inference.
Approach: They propose to modify an example such that a target model makes a wrong prediction by using beam search constrained by heuristic rules and a BERT-masked language model to generate substitution words compatible with the context.
Outcome: The proposed model performance drops dramatically on modified examples, revealing the robustness issue.

Similar Papers

Evaluating Paraphrastic Robustness in Textual Entailment Models (2023.acl-short)

Copied to clipboard

Challenge: Recognizing Textual Entailment models understand language and should be robust to paraphrases.
Approach: They propose to evaluate whether RTE models are robust to paraphrase . they use 1,126 pairs of Recognizing Textual Entailment (RTE) examples to evaluate their models .
Outcome: The evaluation set shows that models change predictions on 8-16% of paraphrased examples, suggesting that there is room for improvement.
Keys to Robust Edits: From Theoretical Insights to Practical Advances (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for modifying parametric memory are prone to inaccuracies due to conflicting or outdated information.
Approach: They propose a plug-and-play module that disentangles editing keys from native model representations and dynamically adjusts keys via contrastive learning to achieve robustness-specificity balance.
Outcome: The proposed method improves over robustness tests by up to 66.4% while maintaining the success rate unaffected.
Improving Paraphrase Detection with the Adversarial Paraphrasing Task (2021.acl-long)

Copied to clipboard

Challenge: a new adversarial method of paraphrase identification is being used to identify paraphrases based on word overlap and syntax . authors propose a dataset that generates semantically equivalent but lexically and syntactically disparate paraphrase pairs .
Approach: They propose an adversarial method for paraphrase identification that uses word overlap and syntax to identify paraphrases.
Outcome: The proposed method improves paraphrase detection accuracy and speed of generation of datasets.
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods to reduce disparities in model outcomes have focused on data augmentation, debiasing model embeddings, or adding fairness-based optimization objectives during training.
Approach: They propose to use certified word substitution robustness methods to improve equality of odds and equality of opportunity on multiple text classification tasks.
Outcome: The proposed methods improve equality of odds and equality of opportunity on multiple text classification tasks.
A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios (2024.findings-emnlp)

Copied to clipboard

Challenge: Using large language models, we evaluated their robustness on multiple datasets.
Approach: They propose a new metric for assessing model robustness by empirical evaluation of several models on multiple datasets.
Outcome: The proposed metric is based on a set of datasets that are constructed by introducing naturally-occurring, non-malicious perturbations or by generating semantically equivalent paraphrases of input questions or statements.
Pointwise Paraphrase Appraisal is Potentially Problematic (2020.acl-srw)

Copied to clipboard

Challenge: prevailing methods for paraphrase identification models are binary classification problems . current methods do not provide consistent and robust performance on unseen samples and real world problems.
Approach: They propose to use binary classification to evaluate paraphrase identification models . they propose to improve methods for fine-tuning BERT models by pairing two sentences as one sequence .
Outcome: The proposed methods may fail on simple tasks like identifying pairs with two identical sentences.
Robustness and Adversarial Examples in Natural Language Processing (2021.emnlp-tutorials)

Copied to clipboard

Challenge: This tutorial aims to raise awareness of practical concerns about NLP robustness . it aims at addressing the weaknesses of NLP systems when faced with adversarial inputs and data with a distribution shift .
Approach: This tutorial aims to bring awareness of practical concerns about NLP robustness . it reviews recent studies on analyzing the weakness of NLP systems when facing adversarial inputs .
Outcome: This tutorial aims to bring awareness of practical concerns about NLP robustness . it will examine the weaknesses of NLP systems when faced with adversarial inputs and data with a distribution shift .
Revisiting Query Variation Robustness of Transformer Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Despite their proficiency with natural language, transformer-based large language models are not robust to query variations such as typos and paraphrases.
Approach: They extend their findings to include more recent large language models . they find that instruct-LLMs are more robust to query variations .
Outcome: The proposed model can be prompted for robustness by a set of instruction-tuned LLMs.
SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions (2020.acl-main)

Copied to clipboard

Challenge: State-of-the-art NLP models can be fooled by human-unaware transformations such as synonymous word substitution.
Approach: They propose a method that constructs a stochastic ensemble by applying random word substitutions on the input sentences and leverages the statistical properties to provably certify the robustness.
Outcome: The proposed method outperforms state-of-the-art methods on IMDB and Amazon text classification tasks with practically meaningful certified accuracy.
Mitigating Paraphrase Attacks on Machine-Text Detection via Paraphrase Inversion (2025.findings-acl)

Copied to clipboard

Challenge: Paraphrases applied to machine-generated texts can degrade performance of machine-text detectors.
Approach: They propose an approach which frames the problem as translation from paraphrased text back to the original text.
Outcome: The proposed approach yields an average improvement of +22% AUROC across seven detectors and three different domains.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations