HejuruUbuyobozi bukurikira
Ibishushanyo RAG hamwe no Gushakisha-Byateguwe
Tekiniki
Ururimi AI
Self-RAG learns when to retrieve and uses reflection tokens to assess passages and generated segments.
Umva iki gitaboAI-byavuzwe · ~2 min
These critiques can guide generation, but they are model predictions rather than independent proof that an answer is correct.
Self-RAG, introduced by Asai and colleagues in 2023, interleaves generation with learned retrieval and critique decisions. Retrieve tokens indicate whether external passages should be fetched. IsRelevant evaluates a passage's relevance; IsSupported predicts whether the generated segment is supported; IsUseful assesses response utility. The method can make retrieval decisions as generation progresses, rather than using only one fixed retrieval step for the whole response. It is compared with fixed-retrieval baselines in the paper, not proof that every other RAG system always retrieves or never checks evidence. Critiques influence candidate selection and can improve results in studied settings, but predicted support can be mistaken and still needs evaluation.
Comparing adaptive retrieval with a baseline that retrieves for every input.
Using predicted passage relevance to score alternative evidence contexts.
Weighting predicted support when choosing generated answer segments.
Evaluating support judgments against independently checked references.
Kubona ibintu neza ni uguhuza na agent RAG, aho moderi itegura gushakisha intambwe nyinshi, ibikoresho byo guhamagara, no kwikosora mugusubiramo. Tegereza guhuza byimazeyo kwinegura hamwe na moderi igenzura, kugarura ibishushanyo mbonera byubumenyi, hamwe no kwiga gushimangira bihesha ibisubizo byizerwa, byatanzwe neza. Nka moderi yo gutekereza ikuze, kubisabwa no kwisuzumisha ubwabyo birashoboka ko bihinduka imyitwarire idasanzwe aho kuba urwego rwihariye, hamwe nurugero ruhitamo ibimenyetso byinshi buri kirego gisaba.
Ibaruwa y'amakuru y'ubuntu
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
Ibisubizo ako kanya kuri buri kibazo, n'icyemezo gishobora gusangirwa gifite ID yagenzurwa umaze gutsinda isomo.
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
Self-RAG learns when to retrieve and uses reflection tokens to assess passages and generated segments. These critiques can guide generation, but they are model predictions rather than independent proof that an answer is correct.
Retrieve tokens support adaptive retrieval. Other RAG designs may also be adaptive, so this contrast is scoped to the fixed-retrieval baseline.
Ibimenyetso byerekana nka IsRelevant, IsSupported, na IsUseful reka icyitegererezo cyo kunegura ibice nibisohoka.
The token is a model-generated support judgment that can guide generation but may be wrong.
Self-RAG yigira kumyitozo yamakuru yatangajwe hamwe nibimenyetso byerekana, bikunze gutangwa numwarimu ushoboye cyane nka GPT-4.
Mu kunegura buri gice kijyanye n'akamaro, Self-RAG irashobora kwirengagiza kugarura ibintu bitari ingingo aho kubishyira mubisubizo.
Komeza wige
Abandi bayobozi batoranijwe kuriyi ngingo
HejuruUbuyobozi bukurikira
Ibishushanyo RAG hamwe no Gushakisha-Byateguwe
Tekiniki