Latest Articles for LLMs

Exploring the role of generative AI in enhancing software safety practices.

A new dataset improves LLMs' ability to follow complex instructions.

Automating ontology population improves knowledge management and accessibility.

AI models are evolving to assist in medical questions, but challenges remain.

Students reflect on using language models in ethical discussions.

This study assesses large language models for generating text inputs in mobile applications.

A new method helps language models generate text faster and more efficiently.

TabSQLify simplifies table reasoning by breaking down large tables for better processing.

This study explores the use of language models for efficient ontology alignment.

TREACLE helps users select the best language models within budget and time limits.

A new benchmark reveals gaps in visual understanding of large language models.

Examining how names influence biases in language models.

This study examines biases in large language models used in healthcare.

A new method for better answers using incomplete knowledge graphs.

EasyLAN streamlines the development of collaborative LLM networks for complex tasks.

In-context QD leverages past successes to create diverse solutions.

A robust Japanese corpus created from Common Crawl data improves LLM performance.

A new system enhances resource sharing among Large Language Models for better performance.

A new method enhances robotic learning by combining language models and reinforcement learning.

A new method uses technology to locate and seal abandoned oil wells.

Introducing a method that enhances data summarization across multiple tables based on user queries.

This study analyzes the effectiveness of LLMs in evaluating AI-generated explanations.

A framework combining human expertise and LLMs to improve qualitative research.

This study assesses how well LLMs can identify and classify technical debt.

A new method to assess politicians' opinions through speech analysis.

Learn how LLMs enhance the efficiency of web-form testing.

Combining LLMs with knowledge graphs enhances answer accuracy in data systems.

Investigating large language models’ effectiveness in translating real-world code into Rust.

A new method improves responses to incomplete user requests using LLMs and logical reasoning.

PathOCL enhances OCL generation accuracy and efficiency for UML class models.

A new benchmark assesses LLMs' abilities in mathematical modeling processes.

Researchers evaluate AI's role in analyzing astronomical data and its implications.

A study reveals the WordGame attack, exploiting weaknesses in LLM safety measures.

A new method offers insights into the trustworthiness of LLM responses.

AGILE enhances LLM agents with memory, expert advice, and real-time tools.

LLM4EA enhances the efficiency of connecting entities in diverse knowledge graphs.

A tool that leverages AI to generate helper assertions for Dafny code verification.

A new framework uses simulated comments to improve fake news detection.

A new framework optimizes the use of large language models efficiently.

A new method speeds up large language model responses using KV cache reuse.