Researchers have developed a new framework for detecting sarcasm in text and images. The framework uses a combination of techniques to identify incons...
Researchers have developed an open benchmark for natural language code retrieval in the 1C:Enterprise ecosystem. This system combines Russian syntax w...
Researchers have developed a new approach to multimodal sentiment analysis that can handle incomplete or corrupted inputs. Their method, called iterat...
Researchers have developed a benchmark called HealMed to evaluate the performance of large language models in medicine across multiple languages. The ...
Researchers propose a framework for evaluating the fairness of language models across different languages. Current evaluation methods focus on English...
Researchers have developed OenoBench, a benchmark for evaluating large language models' knowledge in the wine domain. The benchmark consists of 3,266 ...
Large language models (LLMs) often encounter conflicting evidence from text and numbers when making decisions. Researchers have created a synthetic be...
Researchers have created a benchmark called FormalTCS to evaluate the performance of large language models (LLMs) in conducting end-to-end theoretical...
Researchers have developed a benchmark called ConceptGuard to evaluate the ability of large language models to remove harmful or sensitive knowledge w...
Researchers propose a new framework called HARP for prioritizing vulnerabilities based on specific operational preferences. Unlike existing methods th...
Researchers propose DeltaMomentum, a new method for updating momentum in deep learning optimizers. Unlike traditional exponential moving average (EMA)...
Researchers from Japan investigated whether adding listening behaviors to an AI clone can improve its perceived authenticity. They integrated verbal b...