A new framework called socioduality is proposed to study human-AI interaction. It focuses on the process of how humans and AI systems respond to each ...
Researchers have proposed a new way to evaluate large vision-language models that can both generate images and understand their meaning. Current evalu...
Researchers have found that AI agents can break rules due to how they are framed, the context in which they operate, and social signals. In a study of...
Researchers propose a new approach to federated learning called Split Federated Learning with Client-Specific Sufficiency Estimation. This method aims...
Researchers propose a new approach to improve the performance of conversational recommender systems (CRS) by quantifying the effectiveness of each int...
Researchers have created a benchmark called VSysBench to evaluate how well multimodal large language models (MLLMs) follow system messages. These mess...
Researchers have found that large language models can be biased by irrelevant text. When given extra information not related to the task at hand, thes...
Researchers have created a benchmark for detecting out-of-context misinformation in Nepal. The NepOOC-M benchmark includes 1,090 image-caption pairs t...
Researchers have developed a new Automatic Speech Recognition (ASR) system for the Mizo language. To improve the system's accuracy, they collected and...
Researchers have developed a new approach to detecting statistical watermarks in language models. These watermarks are hidden within the model's outpu...
Researchers have developed SynFlow, an open-source toolkit for analyzing how language usage changes over time. The tool allows for multidimensional an...
Researchers have developed a new benchmark called Hear2Act to evaluate how prosody affects task-oriented dialogue. The benchmark includes 480 scenario...