English
Related papers

Related papers: Perturbing Inputs for Fragile Interpretations in D…

200 papers

Many real world domains require the representation of a measure of uncertainty. The most common such representation is probability, and the combination of probability with logic programs has given rise to the field of Probabilistic Logic…

Artificial Intelligence · Computer Science 2011-07-26 Fabrizio Riguzzi , Terrance Swift

The advent of Large Language Models LLMs marks a milestone in Artificial Intelligence, altering how machines comprehend and generate human language. However, LLMs are vulnerable to malicious prompt injection attacks, where crafted inputs…

Computation and Language · Computer Science 2024-10-29 Sahasra Kokkula , Somanathan R , Nandavardhan R , Aashishkumar , G Divya

Perturbation robustness evaluates the vulnerabilities of models, arising from a variety of perturbations, such as data corruptions and adversarial attacks. Understanding the mechanisms of perturbation robustness is critical for global…

Artificial Intelligence · Computer Science 2025-07-11 Róisín Luo , James McDermott , Colm O'Riordan

Inflectional variation is a common feature of World Englishes such as Colloquial Singapore English and African American Vernacular English. Although comprehension by human readers is usually unimpaired by non-standard inflections, current…

Computation and Language · Computer Science 2021-05-10 Samson Tan , Shafiq Joty , Lav R. Varshney , Min-Yen Kan

Explainable NLP techniques primarily explain by answering "Which tokens in the input are responsible for this prediction?''. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by…

Computation and Language · Computer Science 2023-12-05 Eleftheria Briakou , Navita Goyal , Marine Carpuat

Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong assumptions about the structure of…

Machine Learning · Computer Science 2025-09-30 Yifan Luo , Zhennan Zhou , Bin Dong

Recent breakthroughs in NLP research, such as the advent of Transformer models have indisputably contributed to major advancements in several tasks. However, few works research robustness and explainability issues of their evaluation…

Computation and Language · Computer Science 2022-10-31 Maria Lymperaiou , George Manoliadis , Orfeas Menis Mastromichalakis , Edmund G. Dervakos , Giorgos Stamou

This paper presents a methodology for training a transformer-based model to classify lexical and morphosyntactic features of Skolt Sami, an endangered Uralic language characterized by complex morphology. The goal of our approach is to…

Computation and Language · Computer Science 2024-11-06 Khalid Alnajjar , Mika Hämäläinen , Jack Rueter

State-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of possible transformations scales exponentially with text length,…

Computation and Language · Computer Science 2019-09-04 Robin Jia , Aditi Raghunathan , Kerem Göksel , Percy Liang

While end-to-end learning with fully differentiable models has enabled tremendous success in natural language process (NLP) and machine learning, there have been significant recent interests in learning with latent discrete structures to…

Computation and Language · Computer Science 2022-01-12 Zhaofeng Wu

While neural networks have been successfully applied to many natural language processing tasks, they come at the cost of interpretability. In this paper, we propose a general methodology to analyze and interpret decisions from a neural…

Computation and Language · Computer Science 2017-01-11 Jiwei Li , Will Monroe , Dan Jurafsky

Emotion classification is a challenging task in NLP due to the inherent idiosyncratic and subjective nature of linguistic expression, especially with code-mixed data. Pre-trained language models (PLMs) have achieved high performance for…

Computation and Language · Computer Science 2024-02-06 Kushal Tatariya , Heather Lent , Johannes Bjerva , Miryam de Lhoneux

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Computation and Language · Computer Science 2019-02-01 Thomas Zenkel , Joern Wuebker , John DeNero

Deep neural networks (DNNs) have made significant strides in Natural Language Processing (NLP), yet their interpretability remains elusive, particularly when evaluating their intricate decision-making processes. Traditional methods often…

Computation and Language · Computer Science 2025-12-05 Zhou Yang , Shunyan Luo , Jiazhen Zhu , Fang Jin

Deep learning methods have become very popular for the processing of natural images, and were then successfully adapted to the neuroimaging field. As these methods are non-transparent, interpretability methods are needed to validate them…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Elina Thibeau-Sutre , Sasha Collin , Ninon Burgos , Olivier Colliot

LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains open. We study LLMs through the lens of robustness of their code understanding using a…

Software Engineering · Computer Science 2026-04-21 Claudio Spiess , Prem Devanbu , Earl T. Barr

Research in linguistics has shown that humans can read words with internally scrambled letters, a phenomenon recently dubbed typoglycemia. Some specific NLP models have recently been proposed that similarly demonstrate robustness to such…

Computation and Language · Computer Science 2025-10-27 Gianluca Sperduti , Alejandro Moreo

The ability of transformers to perform precision tasks such as question answering, Natural Language Inference (NLI) or summarising, have enabled them to be ranked as one of the best paradigm to address Natural Language Processing (NLP)…

Computation and Language · Computer Science 2021-05-18 Javier Huertas-Tato , Alejandro Martín , David Camacho

Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction…

Machine Learning · Computer Science 2022-07-18 Xuhong Li , Haoyi Xiong , Xingjian Li , Xuanyu Wu , Xiao Zhang , Ji Liu , Jiang Bian , Dejing Dou

Researchers have relegated natural language processing tasks to Transformer-type models, particularly generative models, because these models exhibit high versatility when performing generation and classification tasks. As the size of these…

Computation and Language · Computer Science 2025-04-04 Fabio Yáñez-Romero , Andrés Montoyo , Armando Suárez , Yoan Gutiérrez , Ruslan Mitkov