Latest Articles for LLMs

Evaluating LLM performance in Mandarin Chinese through a new benchmark called CMMLU.

Exploring the balance between human input and machine learning capabilities.

A dataset designed to assess LLMs' use of external tools for answering questions.

LLMs showcase potential to advance chemistry and materials science through innovative projects.

This article explores how well language models understand programming challenges.

This study assesses language models in medical named entity recognition accuracy.

Examining how personality traits influence language models and their communication.

New model links language understanding with image processing efficiently.

AI chatbots are transforming medical imaging by enhancing efficiency and communication.

New method enhances biomedical concept linking using large language models.

This study evaluates how well LLMs recognize and relate geometric shapes.

Exploring how LLMs can aid in property-based testing for software.

Integrating LLMs in deductive coding streamlines content analysis for researchers.

A study assesses AI's effectiveness in recognizing mental health risks.

This article examines how LLMs handle negated questions and proposes improvements.

Assessing the impact of LLMs on medical tasks and their potential applications.

This study assesses LLMs' ability to create trusted children's stories.

A study assesses the effectiveness of LLMs in interpreting radiology reports.

CrystaLLM leverages AI to speed up crystal structure creation using CIF data.

Investigating if LLMs exhibit human-like personalities through MBTI analysis.

This article discusses using prompts to enhance software traceability with large language models.

Researchers develop methods to identify text created by machines versus humans.

A study on the vulnerabilities of LLM-integrated applications against SQL injection attacks.

A novel approach uses wider networks to improve evaluation quality of language models.

Research highlights LLMs' role in improving medical data extraction and classification.

This research explores how LLMs can process and retrieve GTFS data.

Examining the unpredictable nature of code generation with ChatGPT.

Examining limitations of LLMs in translating code and techniques for improvement.

A new method combines language models and planners for complex tasks.

Exploring recent summit insights on software supply chain security.

Advanced AI tools can be misused for creating malware, raising cybersecurity concerns.

New methods combine fast and slow reasoning for improved visual problem-solving.

A new framework combines LLMs and KGs for better personalized news suggestions.

Learn how to protect software from side-channel attacks using automated tools.

An analysis of the dangers in using language models for medical queries.

AskIt simplifies LLM integration in software projects, improving efficiency and reducing code length.

Examining how LLMs are altering job dynamics in China.

Exploring the role of language models in teaching robots to learn through interaction.

Exploring key issues in how humans and robots communicate.

This study examines how LLMs engage in communication games like Werewolf.