A look into how text quality relates to its probability in language models.
― 7 min read
Computer Science - Computation and Language
RSSIntroducing CHIRON, a character representation system for more engaging storytelling.
― 5 min read
Study reveals gender bias in chatGPT's career suggestions for children.
― 7 min read
SEACrowd aims to improve AI representation for Southeast Asian languages and cultures.
― 7 min read
A novel method optimizing speech analysis and synthesis using vocal tract movements.
― 7 min read
A closer look at how Transformers learn from examples in varying contexts.
― 7 min read
Examining the impact of dialects on language bias detection accuracy.
― 6 min read
This study shows how BERT learns COVID-19 facts through continuous training.
― 4 min read
A dataset for testing image and text connections shows models struggle with text-to-image tasks.
― 6 min read
A new benchmark to assess cultural knowledge in language models across diverse cultures.
― 6 min read
New benchmark evaluates AI models' capabilities in real clinical settings.
― 6 min read
A method to enhance the identification of fake news using social media interactions.
― 7 min read
Exploring the synergy between federated learning and swarm intelligence for improved AI.
― 6 min read
A new method enhances processing of long texts in language models efficiently.
― 9 min read
New methods may refine language model understanding of human preferences.
― 5 min read
A new approach to enhance language models for low-resource languages.
― 6 min read
Exploring how AI improves dialogue-based understanding and response accuracy.
― 4 min read
A novel method improves mental health predictions by analyzing social media posts over time.
― 7 min read
A study evaluates language models on handling multiple tasks simultaneously.
― 7 min read
A new technique improves language models by updating and adding knowledge efficiently.
― 8 min read
Examining the effectiveness of reasoning in large language models.
― 7 min read
A new benchmark tests LLMs' abilities with structured data formats.
― 6 min read
This paper investigates the False Consensus Effect in large language models.
― 5 min read
Twin-Merging improves model merging efficiency and adaptability across various tasks.
― 4 min read
A new framework enhances how LLM agents learn through detailed process guidance.
― 7 min read
A dataset to test language models' grasp of wording differences.
― 5 min read
Introducing RePrompt for better language model performance through optimized prompts.
― 6 min read
Examining the capabilities of LLMs compared to traditional taxonomies.
― 5 min read
This study examines biases in AI models during hate speech data labeling.
― 7 min read
Exploring the role of AI in enhancing grading consistency in online education.
― 8 min read
Examining the need for context in accurate sign language translation.
― 5 min read
This paper introduces a framework to evaluate vulnerabilities in large language models.
― 3 min read
A new benchmark evaluates how language models handle text changes.
― 6 min read
A study on large language models' performance in word grouping challenges.
― 6 min read
Exploring the impact of AI on legal reasoning and decision-making.
― 6 min read
Learn about online speaker diarization and its significance in various applications.
― 6 min read
Introducing a method for interpretable emotional support dialogue systems.
― 6 min read
This method effectively removes copyrighted material while maintaining model performance.
― 6 min read
A clear framework to assess understanding in AI systems.
― 7 min read
Exploring methods to create structured tables using large language models.
― 5 min read