Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Juu ya Umuhimu wa Pembeni

Jaribu alama za ufaafu-anuwai za MMR, uteuzi wa pupa, masasisho ya upunguzaji akiba, na mipaka iliyowekwa na kundi la awali la wagombeaji.

Njia za mwongozo zinazohusianaUpeo wa Umuhimu wa Pembezoni
Swali 1 ya 8

Je, ni tatizo gani la msingi ambalo MMR imeundwa kutatua?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Je, ni tatizo gani la msingi ambalo MMR imeundwa kutatua?
    • Ucheleweshaji wa hoja polepole katika hifadhidata kubwa
    • Tahajia isiyo sahihi katika maswali ya mtumiaji
    • Matokeo yasiyo ya kawaida, yanayokaribia kurudiwa kutoka kwa cheo halisi cha umuhimu
    • Ukosefu wa data ya mafunzo ya upachikaji
  2. Katika fomula ya MMR, thamani ya lambda karibu na 1 inasisitiza nini?
    • Umuhimu kamili kwa swali
    • Upeo tofauti kati ya matokeo
    • Mizani sawa ya wagombea wote
    • Uchaguzi wa nasibu
  3. Je, MMR huchaguaje matokeo yake?
    • Yote mara moja kwa kupanga alama moja
    • Nasibu na mbegu fasta
    • Kwa mpangilio wa alfabeti wa hati
    • Kwa pupa, moja kwa wakati, kulinganisha na vitu vilivyochaguliwa tayari
  4. How can an embedding-based MMR implementation measure query relevance and document redundancy?
    • Using only a document's filename length
    • Using a similarity measure such as cosine, without MMR requiring that one measure universally
    • Using a mandatory audio-transcription score for all text
    • Using no relevance or inter-document comparison at all
  5. Kwa nini MMR ni muhimu sana katika kizazi kilichoongezwa-ugmented (RAG)?
    • Inatoa vijisehemu vya ushahidi wa ziada, usio na kipimo
    • Inapunguza uzito wa mfano
    • Inaboresha muundo wa lugha kiotomatiki
    • Husimba kwa njia fiche hati zilizorejeshwa
  6. If MMR caches each candidate's maximum redundancy and updates it against each new selection, roughly how many similarities are needed for k picks from n candidates?
    • Always constant time independent of k and n
    • Exactly n factorial for every implementation
    • About k times n, ignoring vector dimension and initial setup
    • No document comparisons after the first query score
  7. With lambda equal to 0.5, relevance 0.8, and maximum selected-item similarity 0.9, what is a candidate's MMR scoring term?
    • 0.85, from averaging the two similarities
    • Minus 0.05, from 0.5 times 0.8 minus 0.5 times 0.9
    • 0.72, from multiplying relevance and redundancy
    • 1.7, from adding the two similarities
  8. Can an MMR reranker select a relevant document that the upstream retrieval candidate pool omitted?
    • Yes; diversity scoring invents missing source documents
    • Yes; a lower lambda automatically searches the whole corpus
    • Yes; reranking changes the document's original publication date
    • No; it chooses among the supplied candidates unless the upstream pool is expanded