A fresh method for training code models focusing on semantics and execution behavior.
― 6 min read
Computer Science - Computation and Language
RSSA new framework improves detecting harmful language in online spaces.
― 4 min read
Learn how speech inpainting is restoring audio quality in various fields.
― 6 min read
This research reveals how images and text interact in reasoning tasks.
― 7 min read
A new approach boosts language models' math abilities with speed and accuracy.
― 7 min read
Introducing open grounded planning to improve real-world task execution.
― 9 min read
Examining over-optimization in DAAs and its impact on model performance.
― 7 min read
A new approach to improve user-specific experiences in language models.
― 6 min read
A method to create clear text representations using yes/no questions.
― 4 min read
Examining how language models can help identify Alzheimer's disease early.
― 5 min read
ArguMentor helps readers engage with multiple perspectives in opinion articles.
― 7 min read
This study examines how LLMs handle reasoning in abstract and contextual scenarios.
― 5 min read
Innovative approach to guide large language models using self-assessment.
― 4 min read
The Block Transformer improves text processing speed and efficiency in language models.
― 6 min read
A look at uncertainty types and their importance in language models.
― 5 min read
A look at models that operate without matrix multiplication for better efficiency.
― 6 min read
A new method improves translation quality through effective data augmentation.
― 6 min read
This article presents a new approach to improving language model training efficiency.
― 4 min read
New methods improve how machines recognize emotions in speech.
― 5 min read
Exploring the self-correction processes in language models and their effects.
― 5 min read
This article investigates how language models process verbal aspect in Russian.
― 9 min read
Discover how Extended Mind Transformers improve memory handling in language models.
― 6 min read
This study focuses on improving zero-shot learning through better entity and relation descriptions.
― 3 min read
A new method enhances event resolution by combining language models for better accuracy.
― 5 min read
A new method enhances product search accuracy in online shopping.
― 6 min read
Exploring how LLMs use reasoning to tackle complex tasks.
― 6 min read
New methods aim to enhance reasoning capabilities in language models.
― 6 min read
Recent tests reveal LLMs' weaknesses in simple reasoning despite high benchmark scores.
― 5 min read
Research examines the link between AI explanations and user trust.
― 14 min read
Zyda, a dataset with 1.3 trillion tokens, enhances language model training.
― 5 min read
Conditional finetuning helps language models retain knowledge and reduce bias during training.
― 6 min read
A new framework enhances efficiency in handling requests for LLMs.
― 6 min read
Examining how AI aligns with human touch experiences through textile interaction.
― 5 min read
Bi-Chainer improves accuracy and efficiency in logical reasoning tasks by combining forward and backward methods.
― 7 min read
VulLLM improves automatic detection of software vulnerabilities through advanced learning techniques.
― 6 min read
New metrics shed light on the limitations of language models in representing reality.
― 7 min read
Improving methods for assessing meaning similarity between sentences in natural language.
― 6 min read
A new method to edit language models effectively while maintaining performance.
― 5 min read
This study examines how language models perform language tasks similar to humans.
― 5 min read
A new dataset evaluates Large Language Models' reasoning with complex queries.
― 8 min read