IEEE

ASR Error Correction Using Large Language Models

Abstract: Error correction (EC) models play a crucial role in refining Automatic Speech Recognition (ASR) transcriptions, enhancing the readability and quality of ...
PCMag

AMD Unleashes Ryzen AI 400 Series: 60 TOPS of AI Power Hits Laptops and Mini PCs

The new Ryzen AI 400 series packs Zen 5 cores, RDNA 3.5 graphics, and XDNA 2 NPUs, promising faster AI performance and ...
Microsoft

Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models

Large language models (LLMs), such as Codex, hold great promise in enhancing programming education by automatically generating feedback for students. We investigate using LLMs to generate feedback for ...
IEEE

Selective Error Correction for Activation in Large Language Model Training

Abstract: In Large Language Model (LLM) training, acti-vations constitute a significant portion of memory usage, and memory-side errors occurring in activations can ...
Microsoft

Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models

We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as Constraint Satisfaction ...