Related papers: Simpler becomes Harder: Do LLMs Exhibit a Coherent…

This paper investigates whether the power of the models pre-trained on text data, such as BERT, can be transferred to general token sequence classification applications. To verify pre-trained models' transferability, we test the pre-trained…

The reasoning ability of large language models (LLMs) has been rapidly advancing in recent years, attracting interest in more fundamental approaches that can reliably enhance their generalizability. This work demonstrates that model…

The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable…

We investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how…

Self-consistency (Wang et al., 2023) suggests that the most consistent answer obtained through large language models (LLMs) is more likely to be correct. In this paper, we challenge this argument and propose a nuanced correction. Our…

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code representation, they have been further applied in multiple…

Sentiment understanding has been a long-term goal of AI in the past decades. This paper deals with sentence-level sentiment classification. Though a variety of neural network models have been proposed very recently, however, previous models…

As AI becomes fundamental in sectors like healthcare, explainable AI (XAI) tools are essential for trust and transparency. However, traditional user studies used to evaluate these tools are often costly, time consuming, and difficult to…

In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components,…

Most adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters. Few try to attack classifiers by rewriting a whole sentence, due to the…

Large Language Models (LLMs) changed the way we design and interact with software systems. Their ability to process and extract information from text has drastically improved productivity in a number of routine tasks. Developers that want…

Spaced repetition systems are fundamental to efficient learning and memory retention, but existing algorithms often struggle with semantic interference and personalized adaptation. We present LECTOR (\textbf{L}LM-\textbf{E}nhanced…

The text produced by language models (LMs) can exhibit specific `behaviors,' such as a failure to follow alignment training, that we hope to detect and react to during deployment. Identifying these behaviors can often only be done post…

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

In text classification, creating an adversarial example means subtly perturbing a few words in a sentence without changing its meaning, causing it to be misclassified by a classifier. A concerning observation is that a significant portion…

We propose a new method for evaluating the readability of simplified sentences through pair-wise ranking. The validity of the method is established through in-corpus and cross-corpus evaluation experiments. The approach correctly identifies…

Large Language Models are expressive tools that enable complex tasks of text understanding within Computational Social Science. Their versatility, while beneficial, poses a barrier for establishing standardized best practices within the…

Recently, pre-trained models have achieved state-of-the-art results in various language understanding tasks, which indicates that pre-training on large-scale corpora may play a crucial role in natural language processing. Current…

Large pre-trained language models help to achieve state of the art on a variety of natural language processing (NLP) tasks, nevertheless, they still suffer from forgetting when incrementally learning a sequence of tasks. To alleviate this…