Researchers have discovered that vision-language models (VLMs) designed to balance safe generation behavior with grounded visual reasoning may priorit...
Researchers have created a benchmark for retrieving relevant Greek statutory articles in legal question answering tasks. The new benchmark, called Gre...
Researchers have identified an 'evaluability gap' in AI translation, where even when the source text is shown, it's hard to determine what aspects of ...
Researchers have proposed corrections to Zipf's and Heaps' laws, which describe the distribution of word frequencies in language. The corrections are ...
Researchers have proposed a method to detect hallucinations in large language models. Hallucinations are factual errors generated by these models when...
Researchers have created a dataset called CONSPIRED to study the language patterns of conspiracy theories and how they affect large language models. T...
Researchers have developed a new method for training large language models offline, without requiring online interactions. The approach, called Future...
Researchers have evaluated the effectiveness of Chain-of-Thought (CoT) speech-to-text translation systems in using both spoken words and their transcr...
Researchers have found that the consistency of topic model outputs across repeated runs does not necessarily mean they accurately represent the underl...
Researchers have developed a system called Reinforcement Learning from Community Feedback (RLCF) that enables AI to learn scientific taste. Scientific...
Researchers have developed a framework called KA2L to improve the performance of large language models (LLMs) by assessing their knowledge and focusin...
Large language models (LLMs) are becoming increasingly costly and difficult to improve through human supervision alone. As they approach human-level c...