Latest Articles for Language Models

Study investigates how language models process Italian through multi-task learning.

Investigating how language models handle subject-verb agreement across different languages.

A new approach to make language models concise and effective.

Exploring how LLMs can streamline editing structured documents with minimal effort.

Using LLMs to generate clear features from scientific texts for better predictions.

Research reveals how false information affects language models' reliability and accuracy.

Examining the impact of prompt languages on LLMs in Arabic tasks.

A new approach combines two KenLM models for better data filtering.

Causal language models show promise in solving Sudoku and Zebra puzzles.

A new method enhances language model communication by adjusting personality traits.

SC-Phi2 is a small language model designed for efficient gameplay in StarCraft II.

Enhancing language models for better Arabic dialect generation and cultural awareness.

A study on the effectiveness of automated evaluators for language models.

A new method for improving Arabic LLMs using structured knowledge for better answers.

A tool to assess language models' relevance and appropriateness in Filipino contexts.

New dataset evaluates language models' ability to handle time-aware information.

A new framework assesses medical knowledge in large language models.

This study assesses how well language models assist beginner programmers with code comments.

This study evaluates how well LLMs understand narrative tropes in movie summaries.

This research investigates LLMs' performance in cognitive tasks similar to infant behavior.

Assessing the role of language models in relevance judgments for information retrieval.

A new method for assessing AI agents in customer support via test generation.

This paper presents a framework for improving NER in the Italian language using advanced models.

A study on improving retrieval methods for diverse opinions on complex questions.

Exploring how LLMs struggle with complex coding challenges.

Evaluating LLM performance across long texts in five languages.

A new dataset to improve language models focused on business-related text.

A new method improves detection of texts generated by language models.

A deep look into researchers’ views on using language models in qualitative studies.

A look at how o1 models plan actions and their performance across various tasks.

A look into how word embeddings are analyzed using independent component analysis.

A new method for assessing AI-generated medical explanations using Proxy Tasks.

Exploring how smaller models struggle with inaccuracies from larger counterparts.

LLM-Ref aids researchers in crafting clearer, well-structured papers effortlessly.

Exploring how well AI understands human communication.

Research shows new methods to better align LLMs with human feedback.

A study compares human and AI creativity in storytelling.

Assessing prompt engineering's relevance with new reasoning models.

A look at in-context databases and their potential with language models.

Assessing the role of multilingual models in supporting bilingual students.