Mutauro AI GUIDE

Kudzosera Kutuka muLLMs

Kutukwa kunodzoserwa inzira inokatyamadza yekutadza apo modhi yemutauro inodzidza 'A ndiB' isingakwanise kupindura 'B ndiA.' Inoburitsa kuti maLLM anochengeta chokwadi senge-mwe-directional masangano, kwete seruzivo rwesymmetric.

Teerera kugwaro iriAI-yakarondedzerwa · ~2 min

Pa peji ino2 min verenga
  1. Kudzika Kwakadzika
  2. Kuitwa muNyika yeChokwadi
  3. Ramangwana Rekudzokera Kutuka muLLMs
  4. Kuzvishandisa
  5. Ramba Uchiongorora
  6. Mibvunzo inowanzo bvunzwa

Kudzika Kwakadzika

Yakanyorwa mubepa re2023 naBerglund uye vaanoshanda navo, kutuka kunodzosera kunoratidza kuti kana modhi yakadzidziswa pa 'Amai vaTom Cruise ndiMary Lee Pfeiffer,' inowanzotadza kana yakabvunzwa 'Ndiani mwanakomana waMary Lee Pfeiffer?' kunyange zvazvo mhinduro yacho yakafanana zvine musoro. Mhedzisiro yacho inoenderera kune saizi yemhando uye kunyangwe mushure mekugadzirisa zvakanaka pamazana echokwadi chakadaro. Haisi gaka rekurangarira: modhi yakaona ruzivo, asi mune imwe hurongwa. Nekuti kudzidziswa kunogonesa kufembera kwechiratidzo chinotevera pamusoro peiyo chaiyo yekurongeka kwezwi mu data, iyo nhamba yekubatanidza kubva kuA kusvika kuB haingogadziri chinongedzo kubva kuB kudzokera kuA. Kutsvaga kwakapokana fungidziro yekuti chiyero chega chinoburitsa kuchinjika, kufunga kwemunhu pamusoro pechokwadi.

Kuitwa muNyika yeChokwadi

Chatbot inotaura nemazvo mubereki wemunhu ane mukurumbira asi anotadza kana akakumbirwa kutumidza zita remwana wemubereki ane mukurumbira.

Mumwe muenzaniso unodzokorora 'mutungamiri wechipfumbamwe aiva William Henry Harrison' asi anogumburwa pa 'nhamba ipi mutungamiri aiva William Henry Harrison.'

Mubatsiri wekodhi akadzidza basa-ku-tsananguro mepu haigone kudzoreredza zita rebasa kubva pane tsananguro chete.

A medical QA system yakadzidziswa pa 'Drug X treats Condition Y' inotadza kunyora Mushonga X pawakabvunzwa kuti chii chinobata Condition Y.

Ramangwana Rekudzokera Kutuka muLLMs

Mitigations iri pasi pekudzidza inosanganisira bidirectional data augmentation (kuwedzera zvirevo zvakadzokororwa), zvinangwa zvekudzidzisa zvinofanotaura zviratidzo mumativi ese, uye masisitimu ekudzoreredza anotarisa chokwadi kumusoro anoenderana pane kuvimba nezviremu zvakadzidzwa nemusoro. Zvimwe zvivakwa zvitsva uye reverse-pretraining miedzo inoderedza gaka. Tarisira kuti kutukwa kuderera asi kusapera, sezvo kuchifumura kusawirirana kwakadzama pakati pekudzidza kunotevera-chiratidzo uye symmetric chimiro chehukama hwepasirese.

Kuzvishandisa

Nei zvichikosha

  • Kumhanya uye chiyero. Mutauro workflows inogona kufamba nekukurumidza pasina kupira kuenderana.
  • Svika uye svika. Inopamhidzira kupinda mumitauro yese nemataera ekutaurirana.
  • Sarudzo dzakajeka. Zvikwata zvinogona kupedza nguva yakawanda pakutonga uku otomatiki ichibata kudzokorora.

Chenjera

  • Chokwadi chehuroyi chinogona kupinda chinyararire mishumo, kuyerera kwetsigiro, kana tsvakiridzo.
  • Kunzwa nekukasira kunogona kugadzira mhedzisiro isingaenderane pane zvikumbiro zvakafanana.
  • Sensitive text data inogona kuburitswa kana zvidhiraivho zvisina kusimba.

Matanho anotevera

  1. Tsanangura chimiro chekubuda, toni, uye mhando zviyero usati waburitsa.
  2. Mhinduro dzepasi neakavimbika masosi pese pazvine basa.
  3. Chengetedza ongororo yekuongorora yemunhu kune yakakwira-stake zvinobuda.
  4. Tevera maitiro ekutadza uye dzidzisazve kukurudzira kana mafambiro ebasa nguva nenguva.

Ramba Uchiongorora

Tsamba yemahara

Tora iyo yemazuva ese AI pfupiso

Nhatu dzakasimbiswa dzeAI nyaya mangwanani ega ega pakati pevhiki, dzakanyorwa neChirungu chakajeka. Yemahara zvachose, hapana ads.

Imwe email zuva rega rega revhiki. Bvisa kunyoresa kamwe chete. Hatimbotengese kana kugovera kero yako.

Zviedze iwe pachako

Take the Reversal Curse in LLMs quiz

Mhinduro yepakarepo pamhinduro yega yega, uye chitupa chinogovaniswa chine ID inobatika kana wapedza kosi.

Tanga mibvunzo

Tsigira dzidzo yemahara yeAI. AI Understanding ndeye 501(c)(3) isingabatsiri - hapana ads, hapana paywall, zvachose. Ita chipo

Mibvunzo inowanzo bvunzwa

Chii chinonzi Reversal Curse muLLMs?

Kutukwa kunodzoserwa inzira inokatyamadza yekutadza apo modhi yemutauro inodzidza 'A ndiB' isingakwanise kupindura 'B ndiA.' Inoburitsa kuti maLLM anochengeta chokwadi senge-mwe-directional masangano, kwete seruzivo rwesymmetric.

A model learned “A is B” but fails to answer “B is A.” What is this called?

The paper names this directional failure the reversal curse.

What does the reversal curse show about directional associations?

The paper reports that forward and reverse statements can behave differently.

Is the reversal curse simply a failure because the model never saw the fact?

The research tests failure on a reverse query after forward exposure.

Why might next-token training contribute to the effect?

The paper discusses sequence direction as relevant to the failure.

What does failure on a reverse query imply about model knowledge?

The finding challenges assumptions about flexible use of stored facts.