English
Related papers

Related papers: Competency Problems: On Finding and Removing Artif…

200 papers

NLP models often rely on superficial cues known as dataset biases to achieve impressive performance, and can fail on examples where these biases do not hold. Recent work sought to develop robust, unbiased models by filtering biased examples…

Computation and Language · Computer Science 2023-05-31 Yuval Reif , Roy Schwartz

Interpreting data is central to modern research. Large language models (LLMs) show promise in providing such natural language interpretations of data, yet simple feature extraction methods such as prompting often fail to produce accurate…

Artificial Intelligence · Computer Science 2025-05-30 Michal Bravansky , Vaclav Kubon , Suhas Hariharan , Robert Kirk

Neural networks are known to use spurious correlations such as background information for classification. While prior work has looked at spurious correlations that are widespread in the training data, in this work, we investigate how…

Machine Learning · Computer Science 2022-10-06 Yao-Yuan Yang , Chi-Ning Chou , Kamalika Chaudhuri

With the growing interest in social applications of Natural Language Processing and Computational Argumentation, a natural question is how controversial a given concept is. Prior works relied on Wikipedia's metadata and on content analysis…

Computation and Language · Computer Science 2019-08-21 Benjamin Sznajder , Ariel Gera , Yonatan Bilu , Dafna Sheinwald , Ella Rabinovich , Ranit Aharonov , David Konopnicki , Noam Slonim

Instruction tuning on a mixture of tasks has improved zero-shot capabilities in natural language processing (NLP). Nevertheless, existing methods often learn features that exhibit correlations between instruction-formatted samples and…

Computation and Language · Computer Science 2024-02-12 Lu Chen , Wei Huang , Ruqing Zhang , Wei Chen , Jiafeng Guo , Xueqi Cheng

Pre-trained language models have been successful on text classification tasks, but are prone to learning spurious correlations from biased datasets, and are thus vulnerable when making inferences in a new domain. Prior work reveals such…

Computation and Language · Computer Science 2022-01-03 Huihan Yao , Ying Chen , Qinyuan Ye , Xisen Jin , Xiang Ren

Cryptic crosswords, the dominant crossword variety in the UK, are a promising target for advancing NLP systems that seek to process semantically complex, highly compositional language. Cryptic clues read like fluent natural language but are…

Computation and Language · Computer Science 2025-02-18 Josh Rozner , Christopher Potts , Kyle Mahowald

Large language models (LLMs) have advanced natural language processing (NLP) skills such as through next-token prediction and self-attention, but their ability to integrate broad context also makes them prone to incorporating irrelevant…

Interpretable graph learning has recently emerged as a popular research topic in machine learning. The goal is to identify the important nodes and edges of an input graph that are crucial for performing a specific graph reasoning task. A…

Machine Learning · Computer Science 2026-01-26 Kecheng Cai , Chenyang Xu , Chao Peng , Jiafu Huang , Qiyuan Liang , Irene Zheng

The article describes a model of automatic analysis of puns, where a word is intentionally used in two meanings at the same time (the target word). We employ Roget's Thesaurus to discover two groups of words which, in a pun, form around two…

Computation and Language · Computer Science 2017-07-19 Elena Mikhalkova , Yuri Karyakin

The sarcasm detection task in natural language processing tries to classify whether an utterance is sarcastic or not. It is related to sentiment analysis since it often inverts surface sentiment. Because sarcastic sentences are highly…

Machine Learning · Computer Science 2024-10-17 Lazar Đoković , Marko Robnik-Šikonja

Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious…

Machine Learning · Computer Science 2024-05-07 Guangtao Zheng , Wenqian Ye , Aidong Zhang

Massive language models are the core of modern NLP modeling and have been shown to encode impressive amounts of commonsense and factual information. However, that knowledge exists only within the latent parameters of the model, inaccessible…

Computation and Language · Computer Science 2020-07-03 Pat Verga , Haitian Sun , Livio Baldini Soares , William W. Cohen

Ample evidence suggests that better machine learning models may be steadily obtained by training on increasingly larger datasets on natural language processing (NLP) problems from non-medical domains. Whether the same holds true for medical…

Computation and Language · Computer Science 2020-10-29 Jean-Baptiste Lamare , Tobi Olatunji , Li Yao

Backgrounds in images play a major role in contributing to spurious correlations among different data points. Owing to aesthetic preferences of humans capturing the images, datasets can exhibit positional (location of the object within a…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Mishal Fatima , Steffen Jung , Margret Keuper

Real world data differs radically from the benchmark corpora we use in natural language processing (NLP). As soon as we apply our technologies to the real world, performance drops. The reason for this problem is obvious: NLP models are…

Computation and Language · Computer Science 2016-08-30 Barbara Plank

Few-shot methods for accurate modeling under sparse label-settings have improved significantly. However, the applications of few-shot modeling in natural language processing remain solely in the field of document classification. With recent…

Computation and Language · Computer Science 2022-12-20 Anton Thielmann , Christoph Weisser , Benjamin Säfken

Neurosymbolic systems can satisfy logical constraints during learning without achieving the intended concept-label correspondence; this is a problem known as reasoning shortcuts. We formalize reasoning shortcuts as a constraint satisfaction…

Artificial Intelligence · Computer Science 2026-04-28 Akihiro Takemura , Katsumi Inoue , Masaaki Nishino

While state-of-the-art NLP models have been achieving the excellent performance of a wide range of tasks in recent years, important questions are being raised about their robustness and their underlying sensitivity to systematic biases that…

Computation and Language · Computer Science 2022-03-25 Linyi Yang , Jiazheng Li , Pádraig Cunningham , Yue Zhang , Barry Smyth , Ruihai Dong

Sarcasm detection is a key task for many natural language processing tasks. In sentiment analysis, for example, sarcasm can flip the polarity of an "apparently positive" sentence and, hence, negatively affect polarity detection performance.…

Computation and Language · Computer Science 2017-07-28 Soujanya Poria , Erik Cambria , Devamanyu Hazarika , Prateek Vij