Researchers have proposed a new framework called PrivAct to improve the privacy of large language models in personalized tasks. The existing approache...
Researchers have developed a framework to audit latent bias in generative AI models by analyzing their behavior on specific tasks. They applied this f...
Researchers have developed an evaluation framework called Eval4Sim for assessing the accuracy of simulated human conversations generated by large lang...
Researchers have developed a new framework for automatic speech recognition (ASR) that can handle multiple languages and accents. The system combines ...
Researchers propose that naturalistic reading time can be predicted using simple n-gram statistics rather than complex language model statistics. They...
Researchers have found that self-distillation can sometimes degrade the performance of large language models (LLMs). In mathematical reasoning tasks, ...
Researchers have developed ContextClaim, a new approach to verifiable claim detection. Unlike previous methods that only consider the claim itself, Co...
Researchers have developed DataSTORM, a system that uses large language models to conduct deep research on both structured databases and internet sour...
Researchers have developed TCMIIES, a browser-based tool that uses large language models to extract structured information from academic texts. The sy...
Researchers analyzed how errors from automatic speech recognition (ASR) systems propagate through ASR-LLM cascades in Korean spoken question answering...
Researchers have proposed a new approach to handling long inputs in transformer-based language models. The method, called H^2MT, builds an offline sem...
A new framework uses large language models to improve the accuracy of maintenance records for wind turbines. The system extracts relevant information ...