LATIDIA · Investigación

Potencial de aprendizaje mejorado en las clases de aprendizaje automático mediante la indexación de Wiki LLM

arXiv: 2609.25303v1Tipo de anuncio: nuevo Resumen: Los modelos de lenguaje grandes se implementan cada vez más como tutores específicos del curso, pero su utilidad depende de la base en materiales de instrucción aprobados que a menudo se revisan

La noticia

arXiv:2609.25303v1 Announce Type: new Abstract: Large language models are increasingly deployed as course-specific tutors, but their usefulness depends on grounding in vetted instructional materials that are often revised mid-semester. Our prior work built a multimodal retrieval-augmented generation (RAG) system over an authentic machine learning course corpus (Foundations of Machine Learning) and found that retrieval improved contextual grounding, but that fixed retrieval strategies were suboptimal. That motivates a different question: whether how a corpus is structured at ingest time matters more than how much is retrieved at query time. We present a controlled head-to-head comparison of two knowledge representations over an identical classroom corpus: (A) vector RAG, replicating the best-performing configuration