Enem
PulseAugur coverage of Enem — every cluster mentioning Enem across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
LLM benchmark using ENEM questions shows statistical tie, not clear winner
A benchmark designed to evaluate Large Language Models (LLMs) in Brazilian Portuguese using ENEM 2024 exam questions revealed that a smaller 27-billion parameter model outperformed a 120-billion parameter model. However…
-
New Distill-SFT method improves medical LLM accuracy with controlled rationale transfer
Researchers have developed a controlled workflow called Distill-SFT to improve the accuracy of compact medical language models by carefully selecting teacher rationales. The study found that correct teacher rationales i…
-
Google Gemini launches personalized Study Notebooks for students
Google has introduced a new feature in its Gemini app called Study Notebooks, designed to offer a personalized learning experience for students. Users can upload their study materials, such as notes and syllabi, which G…
-
LLMs encode essay quality representations linearly, study finds
Researchers have investigated how large language models (LLMs) represent essay quality internally, finding that this information is encoded in a linearly accessible form within the models' representations. This informat…