Related papers: Quantifying the Effect of Test Set Contamination o…
Pretraining is the preliminary and fundamental step in developing capable language models (LM). Despite this, pretraining data design is critically under-documented and often guided by empirically unsupported intuitions. To address this, we…
As large language models achieve impressive scores on traditional benchmarks, an increasing number of researchers are becoming concerned about benchmark data leakage during pre-training, commonly known as the data contamination problem. To…
Generative AI is gaining increasing attention in software engineering, where testing remains an indispensable reliability mechanism. According to the widely adopted testing pyramid, unit tests constitute the majority of test cases and are…
Machine learning approaches applied to NLP are often evaluated by summarizing their performance in a single number, for example accuracy. Since most test sets are constructed as an i.i.d. sample from the overall data, this approach overly…
Unit testing is crucial for software development and maintenance. Effective unit testing ensures and improves software quality, but writing unit tests is time-consuming and labor-intensive. Recent studies have proposed deep learning (DL)…
What happens when generative machine learning models are pretrained on web-scale datasets containing data generated by earlier models? Some prior work warns of "model collapse" as the web is overwhelmed by synthetic data; other work…
Generative AI systems have rapidly advanced, with multimodal input capabilities enabling reasoning beyond text-based tasks. In education, these advancements could influence assessment design and question answering, presenting both…
Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random…
Recent advances in Generative Artificial Intelligence (GenAI) have transformed educational content creation, particularly in developing tutor training materials. However, biases embedded in AI-generated content--such as gender, racial, or…
Hampering the interpretation of benchmark scores, evaluation data contamination has become a growing concern in the evaluation of LLMs, and an active area of research studies its effects. While evaluation data contamination is easily…
Ideal summarization models should generalize to novel summary-worthy content without remembering reference training summaries by rote. However, a single average performance score on the entire test set is inadequate in determining such…
The rise of Generative AI (GenAI) tools, such as ChatGPT, has transformed how students access and engage with information, raising questions about their impact on learning outcomes and retention. This study investigates how GenAI (ChatGPT),…
Data sanitization in the context of language modeling involves identifying sensitive content, such as personally identifiable information (PII), and redacting them from a dataset corpus. It is a common practice used in natural language…
Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and…
The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination-unintentional memorization of benchmark data during model training-poses critical…
Text classification is a significant branch of natural language processing, and has many applications including document classification and sentiment analysis. Unsurprisingly, those who do text classification are concerned with the run-time…
Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…
Most language model pre-training frameworks concatenate multiple documents into fixed-length sequences and use causal masking to compute the likelihood of each token given its context; this strategy is widely adopted due to its simplicity…
Generative AI systems have been heralded as tools for augmenting human creativity and inspiring divergent thinking, though with little empirical evidence for these claims. This paper explores the effects of exposure to AI-generated images…
Generative Artificial Intelligence (GAI) models such as ChatGPT have experienced a surge in popularity, attracting 100 million active users in 2 months and generating an estimated 10 million daily queries. Despite this remarkable adoption,…