Related papers: DatedGPT: Preventing Lookahead Bias in Large Langu…
Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…
There is enormous enthusiasm and concerns in using large language models (LLMs) in healthcare, yet current assumptions are all based on general-purpose LLMs such as ChatGPT. This study develops a clinical generative LLM, GatorTronGPT, using…
Large language models (LLMs) have demonstrated great potential in natural language processing tasks within the financial domain. In this work, we present a Chinese Financial Generative Pre-trained Transformer framework, named CFGPT, which…
Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…
This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…
Generative pretraining (the "GPT" in ChatGPT) enables language models to learn from vast amounts of internet text without human supervision. This approach has driven breakthroughs across AI by allowing deep neural networks to learn from…
Existing methods for evaluating large language models face challenges such as data contamination, sensitivity to prompts, and the high cost of benchmark creation. To address this, we propose a lossless data compression based evaluation…
Sentiment analysis is a vital tool for uncovering insights from financial articles, news, and social media, shaping our understanding of market movements. Despite the impressive capabilities of large language models (LLMs) in financial…
Large Language models (LLMs), while powerful, exhibit harmful social biases. Debiasing is often challenging due to computational costs, data constraints, and potential degradation of multi-task language capabilities. This work introduces a…
Vision Language Models (VLMs) struggle with long-form videos due to the quadratic complexity of attention mechanisms. We propose Language-Guided Temporal Token Pruning (LGTTP), which leverages temporal cues from queries to adaptively prune…
Recent deployments of large language models (LLMs) as autonomous trading agents raise questions about whether financial decision-making competence generalizes beyond specific market patterns and how it should be trained and evaluated in…
High-stakes decision making involves reasoning under uncertainty about the future. In this work, we train language models to make predictions on open-ended forecasting questions. To scale up training data, we synthesize novel forecasting…
Large Language Models (LLMs) are pretrained on textual data up to a specific temporal cutoff. This creates a strict knowledge boundary beyond which models cannot provide accurate information without querying external sources. More subtly,…
This paper investigates whether large language models (LLMs) can generate reliable stock market predictions. We evaluate four state-of-the-art models - ChatGPT, Gemini, DeepSeek, and Perplexity - across three prompting strategies: a naive…
With the emerging trend of GPT models, we have established a framework called AutoML-GPT that integrates a comprehensive set of tools and libraries. This framework grants users access to a wide range of data preprocessing techniques,…
Qualitative research delves deeply into individual complex perspectives on technology and various phenomena. However, a meticulous analysis of qualitative data often requires a significant amount of time, especially during the crucial…
Large Language Models (LLMs), typified by OpenAI's GPT, have marked a significant advancement in artificial intelligence. Trained on vast amounts of text data, LLMs are capable of understanding and generating human-like text across a…
Timeseries regression models often struggle to leverage large volumes of labeled multimodal data, particularly when the data are irregularly sampled or contain missing values. This is common in domains like healthcare and predictive…
Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understood. In this work, we study the impact of pre-training…
We assess the ability of GPT -- a large language model -- to serve as a financial robo-advisor for the masses, by using a financial literacy test. Davinci and ChatGPT based on GPT-3.5 score 66% and 65% on the financial literacy test,…