Related papers: Data Augmentations for Improved (Large) Language M…
The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…
Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on understanding of the…
Large Language Models have advanced clinical text classification, but their opaque predictions remain a critical barrier to practical adoption in research and clinical settings where investigators and physicians need to understand which…
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…
Data augmentation methods usually apply the same augmentation (or a mix of them) to all the training samples. For example, to perturb data with noise, the noise is sampled from a Normal distribution with a fixed standard deviation, for all…
We study counterfactual regression, which aims to map input features to outcomes under hypothetical scenarios that differ from those observed in the data. This is particularly useful for decision-making when adapting to sudden shifts in…
We examine the effect of data augmentation for training of language models for speech recognition. We compare augmentation based on global error statistics with one based on per-word unigram statistics of ASR errors and observe that it is…
The rapid development of Large Language Models (LLMs) creates new opportunities for recommender systems, especially by exploiting the side information (e.g., descriptions and analyses of items) generated by these models. However, aligning…
Despite the success of machine learning applications in science, industry, and society in general, many approaches are known to be non-robust, often relying on spurious correlations to make predictions. Spuriousness occurs when some…
Counterfactual explanations (CFs) offer human-centric insights into machine learning predictions by highlighting minimal changes required to alter an outcome. Therefore, CFs can be used as (i) interventions for abnormality prevention and…
A continued issue for those working with computational tools and endangered and under-resourced languages is the lower accuracy of results for languages with smaller amounts of data. We attempt to ameliorate this issue by using data…
Math Word Problem (MWP) solving presents a challenging task in Natural Language Processing (NLP). This study aims to provide MWP solvers with a more diverse training set, ultimately improving their ability to solve various math problems. We…
Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correlations (i.e. confounders), should they be prevalent in the training dataset, rather than on the…
Label distribution (LD) uses the description degree to describe instances, which provides more fine-grained supervision information when learning with label ambiguity. Nevertheless, LD is unavailable in many real-world applications. To…
Advancements in large language models (LLMs) have demonstrated remarkable capabilities across a diverse range of applications. These models excel in generating text completions that are contextually coherent and cover an extensive array of…
Bias in large language models (LLMs) has many forms, from overt discrimination to implicit stereotypes. Counterfactual bias evaluation is a widely used approach to quantifying bias and often relies on template-based probes that explicitly…
Researchers recently found out that sometimes language models achieve high accuracy on benchmark data set, but they can not generalize very well with even little changes to the original data set. This is sometimes due to data artifacts,…
Existing approaches to constructing training data for Natural Language Inference (NLI) tasks, such as for semi-structured table reasoning, are either via crowdsourcing or fully automatic methods. However, the former is expensive and…
Pre-trained large language models (LLM) have emerged as a powerful tool for simulating various scenarios and generating output given specific instructions and multimodal input. In this work, we analyze the specific use of LLM to enhance a…
Data augmentation forms the cornerstone of many modern machine learning training pipelines; yet, the mechanisms by which it works are not clearly understood. Much of the research on data augmentation (DA) has focused on improving existing…