Related papers: Towards Transparency: Exploring LLM Trainings Data…
We present the LM Transparency Tool (LM-TT), an open-source interactive toolkit for analyzing the internal workings of Transformer-based language models. Differently from previously existing tools that focus on isolated parts of the…
Large Language Models (LLMs) offer a promising alternative to traditional survey methods, potentially enhancing efficiency and reducing costs. In this study, we use LLMs to create virtual populations that answer survey questions, enabling…
Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still…
This study addresses the challenges of tracking and analyzing students' learning trajectories, particularly the issue of inadequate knowledge coverage in course assessments. Traditional assessment tools often fail to fully cover course…
We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our…
Large Language Models (LLMs) have shown exceptional performance in text processing. Notably, LLMs can synthesize information from large datasets and explain their decisions similarly to human reasoning through a chain of thought (CoT). An…
The use of knowledge graphs in recommender systems has become one of the common approaches to addressing data sparsity and cold start problems. Recent advances in large language models (LLMs) offer new possibilities for processing side and…
This paper investigates the capabilities of Large Language Models (LLMs) in the context of understanding their knowledge and uncertainty over questions. Specifically, we focus on addressing known-unknown questions, characterized by high…
Machine learning can provide deep insights into data, allowing machines to make high-quality predictions and having been widely used in real-world applications, such as text mining, visual classification, and recommender systems. However,…
We investigate whether Large Language Models (LLMs) exhibit human-like cognitive patterns under four established frameworks from psychology: Thematic Apperception Test (TAT), Framing Bias, Moral Foundations Theory (MFT), and Cognitive…
We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these…
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…
Topic modeling is a state-of-the-art technique for analyzing text corpora. It uses a statistical model, most commonly Latent Dirichlet Allocation (LDA), to discover abstract topics that occur in the document collection. However, the…
Generative AI technologies, particularly Large Language Models (LLMs), have transformed information management systems but introduced substantial biases that can compromise their effectiveness in informing business decision-making. This…
We propose a novel approach for decision making problems leveraging the generalization capabilities of large language models (LLMs). Traditional methods such as expert systems, planning algorithms, and reinforcement learning often exhibit…
Large language models have revolutionized natural language processing with their surprising capability to understand and generate human-like text. However, many of these models inherit and further amplify the biases present in their…
This paper embarks on an exploration into the Large Language Model (LLM) datasets, which play a crucial role in the remarkable advancements of LLMs. The datasets serve as the foundational infrastructure analogous to a root system that…
Topic modeling has become a crucial method for analyzing text data, particularly for extracting meaningful insights from large collections of documents. However, the output of these models typically consists of lists of keywords that…
The performance of large language models (LLMs) is significantly affected by the quality and composition of their pre-training data, which is inherently diverse, spanning various languages, sources, and topics. Effectively integrating these…
We present a benchmark for large language models designed to tackle one of the most knowledge-intensive tasks in data science: writing feature engineering code, which requires domain knowledge in addition to a deep understanding of the…