Introducing a new scale for evaluating emotional depth in storytelling.
― 8 min read
Computer Science - Computation and Language
RSSA method to evaluate model knowledge through internal processing.
― 7 min read
Hierarchical Prompting Taxonomy improves evaluation methods for language models.
― 6 min read
DetectBench evaluates LLMs on their ability to detect hidden evidence in reasoning tasks.
― 5 min read
Introducing SeTAR, a training-free solution for detecting out-of-distribution data in neural networks.
― 7 min read
A study on using LLMs to judge other LLMs and its implications.
― 7 min read
Explore the impact of IA research on natural language processing.
― 6 min read
PromptDSI improves document retrieval by efficiently managing new and existing information.
― 6 min read
A new method improves machine translation for underrepresented languages.
― 5 min read
MultiSocial dataset aids in detecting machine-generated texts across 22 languages.
― 6 min read
P-Tailor customizes language models using the Big Five Personality Traits.
― 6 min read
This article discusses how deep neural networks learn language through next-token prediction.
― 7 min read
FuseGen combines multiple models for better quality synthetic data in machine learning.
― 7 min read
Synthetic data enhances the accuracy of stance detection in online discussions.
― 7 min read
A new method to improve model stability and performance in low-resource settings.
― 6 min read
IPEval assesses language models' understanding of intellectual property concepts.
― 5 min read
New methods are improving communication for the deaf community through enhanced sign language recognition.
― 6 min read
Snap helps large language models unlearn specific information while keeping their performance.
― 7 min read
This article reviews FS-GEN, combining large and small models for better outcomes.
― 7 min read
A framework to assess language models' factual accuracy and reliability.
― 8 min read
This study assesses LLM therapists from clients' perspectives using simulated interactions.
― 7 min read
LLMs can aid in social engineering protection and also pose new risks.
― 6 min read
A new technique enhances anomaly detection using self-supervised learning.
― 7 min read
Examining how prompts affect reasoning in large language models.
― 6 min read
UNCTAD creates an open-source RAG tool for better data access and efficiency.
― 6 min read
A new model generates Czech poetry with improved rhyme and rhythm.
― 6 min read
LLM-A* merges traditional algorithms with language models for efficient path planning.
― 6 min read
SAFER improves predictions in knowledge graphs with limited examples.
― 6 min read
A new benchmark evaluates reasoning skills in language models.
― 7 min read
WavRx analyzes speech for health while protecting privacy, showing promising diagnostic results.
― 7 min read
A new approach to improve medical dialogue systems aligns with clinician reasoning.
― 6 min read
A rich dataset of 2.7 million news articles from 1878 to 1977.
― 7 min read
A study on how language models generate persuasive rationales for argument evaluation.
― 5 min read
Two new models aim to improve technology access for Galician speakers.
― 5 min read
Examining how LLMs process reasoning tasks effectively.
― 7 min read
Exploring the role of language models in processing structured data.
― 6 min read
A new method enhances Alzheimer's risk prediction using electronic health records and advanced models.
― 8 min read
A new method improves how AI models understand spatial relationships.
― 5 min read
Explore how technology is reshaping mental health support and care.
― 4 min read
FoRAG aims to improve answer accuracy and logical structure in long-form responses.
― 5 min read