Cuestionario vinculado a una guía · fácil Nivel
Fechas límite de conocimientos en el cuestionario de LLM
Prueba qué es un límite de conocimiento, por qué los modelos juzgan mal su propia fecha límite y cómo la búsqueda, la recuperación y la inyección de fecha mantienen las respuestas actualizadas.
Pregunta 1 de 8
¿Cuál es el límite de conocimiento de un modelo?
Vista previa de cada pregunta8 preguntas
Las respuestas y explicaciones aparecen a medida que realiza el cuestionario.
- ¿Cuál es el límite de conocimiento de un modelo?
- The date the model stops working
- The approximate date after which its training data contains little or no information
- The date the model was released to the public
- The date the vendor ends customer support
- ¿Por qué los modelos a menudo no están seguros de su propio límite o lo subestiman?
- Vendors deliberately hide it from the model
- Models delete their most recent data after training
- Models count days incorrectly
- The final months before the cutoff are thinly represented, because people keep writing about events long afterward
- ¿Cuál es la forma más fiable de averiguar el límite de conocimiento de un modelo?
- Check the vendor's published model documentation
- Ask the model directly
- Count the words in its answers
- Look at the model's logo
- ¿Qué solución simple corrige muchos casos en los que un modelo asume una fecha actual incorrecta?
- Fine-tuning the model every week
- Turning the model off and on
- Putting the current date in the system prompt
- Using shorter prompts
- Un chatbot con navegación web responde a una pregunta sobre las noticias de la semana pasada. ¿Cuál afirmación es correcta?
- Its training cutoff has moved to last week
- It can no longer make factual errors
- It retrains itself on every query
- Its training cutoff is unchanged; it is reading new sources and is only as accurate as the pages it retrieves
- Why is retrieval usually preferred over fine-tuning for keeping facts current?
- Fine-tuning is slower and more costly as a way to keep facts current
- Fine-tuning is impossible for large models
- Retrieval permanently changes the model's weights
- Retrieval works without any documents
- Which of these is a typical sign of stale knowledge?
- The model refuses every question
- The model switches to another language
- The model names an outdated software version as the latest
- The model's answers are unusually short
- When building evals for cutoff-related problems, what should you include?
- Only questions about events well before the cutoff
- Questions whose correct answers changed after the cutoff
- Questions with all dates removed
- A question asking the model to state its cutoff