Latest Articles for LLMs

This paper presents a new approach to enhance KGQA performance using GNNs and LLMs.

Introducing open grounded planning to improve real-world task execution.

A method to create clear text representations using yes/no questions.

A new method enhances event resolution by combining language models for better accuracy.

A new system for assessing language models using real-world data streams.

A study compares empathetic responses of language models and humans.

This article examines how LLMs understand human beliefs and feelings.

Using AI to automate vectorization, enhancing code efficiency and correctness.

Jamming attacks can disrupt retrieval-augmented generation systems by blocking responses.

This study examines how social perceptions affect student interactions with LLMs in programming courses.

LogBatcher simplifies log parsing using large language models without prior training.

A new benchmark tests LLMs' ability to find software vulnerabilities.

Exploring how machines detect opinions in social media posts.

A look into how LLMs tackle programming by example challenges.

Assessing LLMs' role in improving structured representation of scientific papers.

A new method improves processing of text-rich graphs for better insights.

Investigating how LLM predictions align with human choices using statistical modeling.

This article explores using AI to improve multi-objective optimization processes.

Evaluating risks of biased outcomes in robots using language models.

SciEx reveals strengths and challenges of LLMs in scientific evaluation.

This study evaluates how LLMs can enhance mutation testing in software development.

A new benchmark tests LLMs' abilities with structured data formats.

This paper investigates the False Consensus Effect in large language models.

Introducing RePrompt for better language model performance through optimized prompts.

This study examines biases in AI models during hate speech data labeling.

Exploring the role of AI in enhancing grading consistency in online education.

Research shows consistent response styles improve LLM effectiveness with fewer examples.

A new method combines human and AI for efficient text classification.

This study analyzes how language influences cultural values in large models.

APPL streamlines development with large language models using an intuitive, Python-like syntax.

This article discusses how deep neural networks learn language through next-token prediction.

UNCTAD creates an open-source RAG tool for better data access and efficiency.

This study investigates the effectiveness of FActScore in multiple languages.

CEBench helps businesses and researchers assess LLMs while managing costs and performance.

GIEBench assesses LLMs' empathetic responses based on diverse group identities.

A study on PlagBench and its role in detecting plagiarism in LLM outputs.

A new dataset assesses LLM performance in solving graph-related challenges.

This paper showcases a method for using LLMs to annotate tabular data with minimal human effort.

This study examines LLMs as a cost-effective alternative for text classification.

LLaMIPa enhances computers' ability to grasp conversation dynamics.