Researchers have developed DeepTCM1.0, a multi-expert AI agent that can decipher the mechanisms of traditional Chinese medicine (TCM) compound formula...
StocksTalk is a voice-enabled conversational system that can turn spoken financial requests into executable queries over real-world market data. It co...
Researchers studied how a large language model called Qwen3-4B expresses confidence in its answers. They found that the model tends to be overly confi...
Researchers from the University of Guayaquil and MIT conducted three experiments to investigate whether large language models (LLMs) discriminate agai...
Researchers have found that large language models (LLMs) can behave in unexpected ways when given new information in a medical allocation scenario. In...
Researchers have developed a model called Brain2Qwerty v2 that can accurately decode natural sentences from non-invasive brain recordings. The model u...
Researchers have developed a new method for detecting token-level hallucinations in generated text. This approach treats hallucination as a temporally...
The Global Index on Responsible AI (GIRAI) has released its 2nd Edition methodology. The index assesses responsible AI governance across five dimensio...
Researchers have conducted a systematic mapping study on language models developed for the Portuguese language. They analyzed 46 models across various...
Researchers have found that large language models (LLMs) tend to use deontic modals like 'must', 'should', and 'have to' less frequently than humans d...
Researchers have proposed a new method called Entropy-Constrained Adaptive Stochastic Quantization (ECASQ) to improve the efficiency of data and machi...
Researchers have developed TokenPowerSandbox, an evidence-gated workflow for energy-aware large language model serving. The system uses a CPU-resident...