English
Related papers

Related papers: Perturbing Inputs for Fragile Interpretations in D…

200 papers

One way to interpret neural model predictions is to highlight the most important input features---for example, a heatmap visualization over the words in an input sentence. In existing interpretation methods for NLP, a word's importance is…

Computation and Language · Computer Science 2022-09-07 Shi Feng , Eric Wallace , Alvin Grissom , Mohit Iyyer , Pedro Rodriguez , Jordan Boyd-Graber

Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the…

Machine Learning · Computer Science 2018-05-09 Motoki Sato , Jun Suzuki , Hiroyuki Shindo , Yuji Matsumoto

Word embeddings are a powerful natural language processing technique, but they are extremely difficult to interpret. To enable interpretable NLP models, we create vectors where each dimension is inherently interpretable. By inherently…

Computation and Language · Computer Science 2021-09-29 Adly Templeton

Many adversarial attacks in NLP perturb inputs to produce visually similar strings ('ergo' $\rightarrow$ '$\epsilon$rgo') which are legible to humans but degrade model performance. Although preserving legibility is a necessary condition for…

Computation and Language · Computer Science 2023-03-14 Dev Seth , Rickard Stureborg , Danish Pruthi , Bhuwan Dhingra

Gradient-based analysis methods, such as saliency map visualizations and adversarial input perturbations, have found widespread use in interpreting neural NLP models due to their simplicity, flexibility, and most importantly, their…

Computation and Language · Computer Science 2020-10-13 Junlin Wang , Jens Tuyls , Eric Wallace , Sameer Singh

While vector-based language representations from pretrained language models have set a new standard for many NLP tasks, there is not yet a complete accounting of their inner workings. In particular, it is not entirely clear what aspects of…

Computation and Language · Computer Science 2021-04-16 Matteo Alleman , Jonathan Mamou , Miguel A Del Rio , Hanlin Tang , Yoon Kim , SueYeon Chung

Modern Natural Language Processing (NLP) models are known to be sensitive to input perturbations and their performance can decrease when applied to real-world, noisy data. However, it is still unclear why models are less robust to some…

Computation and Language · Computer Science 2022-03-21 Yunxiang Zhang , Liangming Pan , Samson Tan , Min-Yen Kan

Linguistic representation learning in deep neural language models (LMs) has been studied for decades, for both practical and theoretical reasons. However, finding representations in LMs remains an unsolved problem, in part due to a dilemma…

Computation and Language · Computer Science 2026-03-26 Joshua Rozner , Cory Shain

Neural networks are widely regarded as black-box models, creating significant challenges in understanding their inner workings, especially in natural language processing (NLP) applications. To address this opacity, model explanation…

Computation and Language · Computer Science 2025-01-10 Melkamu Mersha , Mingiziem Bitewa , Tsion Abay , Jugal Kalita

Recent research has adopted a new experimental field centered around the concept of text perturbations which has revealed that shuffled word order has little to no impact on the downstream performance of Transformer-based language models…

Computation and Language · Computer Science 2023-10-04 Ekaterina Taktasheva , Vladislav Mikhailov , Ekaterina Artemova

Recent research analyzing the sensitivity of natural language understanding models to word-order perturbations has shown that neural models are surprisingly insensitive to the order of words. In this paper, we investigate this phenomenon by…

Computation and Language · Computer Science 2022-04-01 Louis Clouatre , Prasanna Parthasarathi , Amal Zouaq , Sarath Chandar

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…

Machine Learning · Computer Science 2024-12-30 Navid Nayyem , Abdullah Rakin , Longwei Wang

Social media platforms like Twitter have increasingly relied on Natural Language Processing NLP techniques to analyze and understand the sentiments expressed in the user generated content. One such state of the art NLP model is…

Computation and Language · Computer Science 2025-04-03 Akil Raj Subedi , Taniya Shah , Aswani Kumar Cherukuri , Thanos Vasilakos

Current methods for Black-Box NLP interpretability, like LIME or SHAP, are based on altering the text to interpret by removing words and modeling the Black-Box response. In this paper, we outline limitations of this approach when using…

Computation and Language · Computer Science 2022-08-09 Yves Rychener , Xavier Renard , Djamé Seddah , Pascal Frossard , Marcin Detyniecki

Large Language Models (LLMs) excel in text classification, but their complexity hinders interpretability, making it difficult to understand the reasoning behind their predictions. Explainable AI (XAI) methods like LIME and SHAP offer local…

Computation and Language · Computer Science 2025-07-16 Yogachandran Rahulamathavan , Misbah Farooq , Varuna De Silva

The relationship between communicated language and intended meaning is often probabilistic and sensitive to context. Numerous strategies attempt to estimate such a mapping, often leveraging recursive Bayesian models of communication. In…

Computation and Language · Computer Science 2023-05-03 Benjamin Lipkin , Lionel Wong , Gabriel Grand , Joshua B Tenenbaum

Neural Machine Translation (NMT) has reached a level of maturity to be recognized as the premier method for the translation between different languages and aroused interest in different research areas, including software engineering. A key…

Computation and Language · Computer Science 2022-03-31 Pietro Liguori , Cristina Improta , Simona De Vivo , Roberto Natella , Bojan Cukic , Domenico Cotroneo

Large language models (LLMs) achieve strong performance across many natural language processing tasks, yet their decision processes remain difficult to interpret. This lack of transparency creates challenges for trust, debugging, and…

Computation and Language · Computer Science 2026-04-20 Venkata Abhinandan Kancharla

There has been increasing interest in evaluations of language models for a variety of risks and characteristics. Evaluations relying on natural language understanding for grading can often be performed at scale by using other language…

Computation and Language · Computer Science 2023-12-11 Simon Lermen , Ondřej Kvapil

We propose a general method to break down a main complex task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to the final target task. Our method allows for representing…

Computation and Language · Computer Science 2024-02-02 Felipe Urrutia , Cristian Buc , Valentin Barriere
‹ Prev 1 2 3 10 Next ›