Related papers: Estimating Privacy Leakage of Augmented Contextual…
To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perform this integration in a predictable way across different…
Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…
The adoption of generative AI in education has accelerated dramatically in recent years, with Large Language Models (LLMs) increasingly integrated into learning environments in the hope of providing personalized support that enhances…
Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…
Large Language Models have been shown to demonstrate stereotypical biases in their representations and behavior due to the discriminative nature of the data that they have been trained on. Despite significant progress in the development of…
Contextual Bandits find important use cases in various real-life scenarios such as online advertising, recommendation systems, healthcare, etc. However, most of the algorithms use flat feature vectors to represent context whereas, in the…
The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…
Large language models have demonstrated strong capabilities to learn in-context, where exemplar input-output pairings are appended to the prompt for demonstration. However, existing work has demonstrated the ability of models to learn…
Large language models (LLMs) can sometimes report the strategies they actually use to solve tasks, yet at other times seem unable to recognize those strategies that govern their behavior. This suggests a limited degree of metacognition -…
In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLM's response,…
The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…
Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning…
Cascades are a common type of machine learning systems in which a large, remote model can be queried if a local model is not able to accurately label a user's data by itself. Serving stacks for large language models (LLMs) increasingly use…
Large language models leverage both parametric knowledge acquired during pretraining and in-context knowledge provided at inference time. Crucially, when these sources conflict, models arbitrate based on their internal confidence,…
As the modern tools of choice for text understanding and generation, large language models (LLMs) are expected to accurately output answers by leveraging the input context. This requires LLMs to possess both context-faithfulness and factual…
Although large language models (LLMs) have tremendous utility, trustworthiness is still a chief concern: models often generate incorrect information with high confidence. While contextual information can help guide generation, identifying…
Large Language Models (LLMs) have demonstrated extraordinary capabilities and contributed to multiple fields, such as generating and summarizing text, language translation, and question-answering. Nowadays, LLM is becoming a very popular…
Citation practices are crucial in shaping the structure of scientific knowledge, yet they are often influenced by contemporary norms and biases. The emergence of Large Language Models (LLMs) introduces a new dynamic to these practices.…
Masked Language Models (MLMs) have achieved remarkable success in many self-supervised representation learning tasks. MLMs are trained by randomly masking portions of the input sequences with [MASK] tokens and learning to reconstruct the…
Large language models (LLMs) and AI agents are increasingly integrated into enterprise systems to access internal databases and generate context-aware responses. While such integration improves productivity and decision support, the model…