quiz bu lëkkale ak tegtal · Yomb Niveau

Bisu dagg xam-xam ci LLMs Quiz

Dafay saytu liy dagg xam-xam, lu tax model yi di juum ci seen bis cutoff, ak ni seetlu, jëlaat ak injection date di tëye tontu yi ci jamono.

Yooni njiit yu jëm ciBisu dagg xam-xam ci LLMs
Laaj 1 de 8

Luy dagg xam-xam bu benn model?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Luy dagg xam-xam bu benn model?
    • 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
  2. Lan moo waral model yi duñu gëm, wala ñuy suufeel seen cutoff?
    • 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
  3. Lan mooy anam wi gëna wóor ngir gis dagg xam-xam bu benn model?
    • Check the vendor's published model documentation
    • Ask the model directly
    • Count the words in its answers
    • Look at the model's logo
  4. Lan mooy saafara lu yomb luy saafara jafe-jafe yu bari ci model buy xalaat bis bi juum?
    • Fine-tuning the model every week
    • Turning the model off and on
    • Putting the current date in the system prompt
    • Using shorter prompts
  5. Chatbot bu am navigasioŋ ci web bi dafay tontu benn laaj bu jëm ci xibaaru ayu-bis bi weesu. Ban wax moo dëggu?
    • 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
  6. 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
  7. 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    • The model names an outdated software version as the latest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
  8. 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