Browse Articles

Large language models are increasingly used to solve math problems, but their ability to handle multi-step reasoning remains uncertain. In this study, students tested whether different prompting styles could improve LLM accuracy on challenging AIME math questions and found that detailed step-by-step solutions did not significantly outperform simpler prompts. These results suggest that improving LLM mathematical reasoning may require deeper model-level advances rather than changes in prompting style alone.

Here, the authors investigated the integration of large language models (LLMs) with drug target affinity predictors (DTAPs) to improve drug repurposing, demonstrating a significant increase in prediction accuracy, particularly with GPT-4, for psychotropic drugs and the sigma-1 receptor. This novel approach offers to potentially accelerate and reduce the cost of drug discovery by efficiently identifying new therapeutic uses for existing drugs.

This article describes the classification of medical text data using vector databases and text embedding. Various large language models were used to generate this medical data for the classification task.

In this study, we investigated how the complexity of a query can influence tool-use hallucinations in large language models that were tasked with setting an appointment. Using explainable AI (XAI) as a tool to test the hypothesis, we analyzed trends in hallucination rates by the type of query and saw results that when complexity and ambiguity of the query increased (such as asking for multiple days or unclear time ranges), the model was more likely to make errors due to misunderstanding time-related data from tool outputs. This shows that making large language models (LLMs) understand what seems logical to a human is still difficult, especially in complex tasks, and that knowing what causes these errors can help build more trustworthy AI systems.

Authors examine the effectiveness of Large Language Models (LLMs) like BERT, MathBERT, and OpenAI GPT-3.5 in assisting middle school students with math word problems, particularly following the decline in math performance post-COVID-19.

Machine translation remains a challenging area in artificial intelligence, with neural machine translation (NMT) making significant strides over the past decade but still facing hurdles, particularly in translation quality due to the reliance on expensive bilingual training data. This study explores whether large language models (LLMs), like GPT-4, can be effectively adapted for translation tasks and outperform traditional NMT systems.

Various methods exist to mitigate bias in AI models, including "Constitutional AI," a technique which guides the AI to behave according to a list of rules and principles. Lo, Poosarla, Singhal, Li, Fu, and Mui investigate whether constitutional AI can reduce bias in AI outputs on political topics.