Ururimi AI

HyDE Hypothetical Document Embeddings

HyDE itezimbere kugarura ubanza gusaba icyitegererezo cyururimi kwiyumvisha inyandiko y'ibisubizo mpimbano, hanyuma ugashakisha hamwe ninyandiko yashyizwemo aho kubaza ikibazo kibisi.

Umva iki gitaboAI-byavuzwe · ~2 min

Kuriyi page2 min soma
  1. Incamake
  2. Kwibira cyane
  3. Gushyira mu bikorwa Isi
  4. Kazoza ka HyDE Hypothetical Document Embeddings
  5. Kubishyira mubikorwa
  6. Komeza Ubushakashatsi
  7. Ibibazo bikunze kubazwa

Incamake

It bridges the gap between short questions and the longer passages you actually want to find.

Kwibira cyane

HyDE was proposed by Gao and colleagues in 2022 for dense retrieval without relevance labels. It asks an instruction-following language model to generate a hypothetical answer document, embeds that text with an unsupervised contrastive encoder such as Contriever, and searches the actual corpus for similar vectors. The hypothetical document can supply document-like topical patterns even when its details are false. The paper describes the dense encoder as a bottleneck that can reduce the influence of invented details; this is not a guarantee that errors never affect retrieval. Evaluate real retrieved passages rather than treating the generated text as factual evidence. HyDE targets a query-to-document mismatch and reported strong results on tested tasks and languages, without implying universal superiority over trained retrievers.

Gushyira mu bikorwa Isi

Zeru-shoti kugarura muri domaine nshya aho nta kimenyetso cyanditseho ikibazo-cyamahugurwa gihari

Gushakisha indimi nyinshi, kubyara hypothettike igisubizo mururimi rugenewe mbere yo gushiramo

Gutezimbere RAG kwibutsa mukwagura terse ibibazo byabakoresha mubukire bwa pseudo-inyandiko

Ubushakashatsi nubushakashatsi bwemewe aho ibibazo bigufi bigomba guhuza ibice byinshi, jargon-iremereye

Kazoza ka HyDE Hypothetical Document Embeddings

HyDE ni inyubako yubaka mumiyoboro ya RAG igezweho, akenshi ihujwe na reranking hamwe nibibazo byinshi. Tegereza impinduka zitanga inyandiko nyinshi zimpuzandengo kandi ugereranije ibyo bashizemo kugirango bakomere, gukoresha imihindagurikire y'ikirere itera HyDE gusa mugihe ikibazo kibisi cyagaruye nabi, hamwe no guhuza hamwe na LLM zahendutse zaho kugirango ugabanye ubukererwe nigiciro. Mugihe ibyitegererezo bibyara umusaruro bigenda byiyongera, ubwiza bwinyandiko - kandi rero kugarura - bigomba gukomeza kuzamuka.

Kubishyira mubikorwa

Impamvu ari ngombwa

  • Umuvuduko n'igipimo. Ururimi rwakazi rushobora kugenda byihuse nta gutamba guhuzagurika.
  • Kugera no kugera. Yagura uburyo bwindimi nuburyo bwo gutumanaho.
  • Ibyemezo bisobanutse. Amakipe arashobora kumara umwanya munini murubanza mugihe automatike ikora gusubiramo.

Witondere

  • Ibintu bifatika bishobora kwinjiza bucece raporo, gushyigikira imigendekere, cyangwa ibisubizo byubushakashatsi.
  • Kwihuta byihuse birashobora gukora ibisubizo bidahuye mubisabwa bisa.
  • Ibyanditswe byumvikana birashobora kugaragara niba kugenzura kugenzura ari ntege.

Intambwe ikurikira

  1. Sobanura imiterere isohoka, amajwi, hamwe nubuziranenge mbere yo gutangira.
  2. Ibisubizo byibanze hamwe nisoko yizewe igihe cyose ukuri kwingirakamaro.
  3. Komeza kugenzura abantu kugenzura ibisubizo byinshi.
  4. Kurikirana uburyo bwo kunanirwa no kongera imyitozo cyangwa akazi gahoraho.

Komeza Ubushakashatsi

Ibaruwa y'amakuru y'ubuntu

Ibuka amakuru ya buri munsi ya AI

Inkuru eshatu zizewe za AI buri gitondo cy'iminsi y'akazi, zanditse mu rurimi rworoshye. Ubuntu iteka ryose, nta kwamamaza.

Imeri imwe buri munsi y'akazi. Kwiyimura mu buryo bumwe. Ntitwigera tugurisha cyangwa ngo dusangire aderesi yawe.

Isuzume

Take the HyDE Hypothetical Document Embeddings quiz

Ibisubizo ako kanya kuri buri kibazo, n'icyemezo gishobora gusangirwa gifite ID yagenzurwa umaze gutsinda isomo.

Tangira ikibazo

Fasha uburezi bwa AI bw'ubuntu. AI Understanding ni umuryango utegamiye kuri leta wa 501(c)(3) — nta kwamamaza, nta kwishyura, iteka ryose. Tanga impano

Ibibazo bikunze kubazwa

What is HyDE Hypothetical Document Embeddings?

HyDE itezimbere kugarura ubanza gusaba icyitegererezo cyururimi kwiyumvisha inyandiko y'ibisubizo mpimbano, hanyuma ugashakisha hamwe ninyandiko yashyizwemo aho kubaza ikibazo kibisi. Ikemura icyuho kiri hagati yibibazo bigufi nibice birebire ushaka kubona.

Niki HyDE itanga mbere yo gukora retrake?

HyDE isaba LLM kwandika inyandiko isubiza hypothettike, iyinjizamo noneho ikoreshwa mugushakisha ibice nyabyo.

Ni uruhe ruhare rugenewe rwa kodegisi ya koderi mugihe inyandiko ya hypothetique ya HyDE irimo ibisobanuro byahimbwe?

The paper motivates the dense bottleneck as filtering details, but a generated error can still change the representation and retrieved results.

Ni ubuhe bwoko bwo gushyiramo moderi bukoreshwa muri HyDE yumwimerere kugirango ushireho inyandiko ya hypothettike?

HyDE ikora generator ya LLM hamwe na kodegisi itagenzuwe nka Contriever kugirango ushiremo inyandiko.

Ni ikihe kibazo cyibanze mugushakisha kwinshi HyDE yagenewe gukemura?

Muguhindura ikibazo mubyandiko bisa ninyandiko, HyDE yimura vector yubushakashatsi hafi yubwoko ibice bigomba guhura.

Nigute variant ya HyDE ishobora guhuza inyandiko nyinshi zakozwe hypothettike muburyo bumwe bwo gushakisha?

Combining embeddings is one way to aggregate generated samples; it does not guarantee improved retrieval on every query.