Dan Bareket

[Dan Bareket @dbreqt]

@aarontay Yes incorporating mentions is kind of a hit-or-miss, it can be crucial for some papers (e.g. when necessary info wasn't retrieved from the index), but it tends to be confusing for models to differentiate consistently

[Dan Bareket @dbreqt]

@aarontay @pastaraspberry @menhguin @PradyuPrasad Appreciate the feedback Aaron (I'm from the Ai2 paperfinder crew). Btw we've been slowly fixing small issues based on the usage we're seeing. Current version should have a more clear and expected behaviour on some things you pointed out re the initial release. Still WIP ofc

[Dan Bareket @dbreqt]

@Zorkimer @allen_ai Will do

[Dan Bareket @dbreqt]

Give it a shot. If it didn't find what you wanted in the first go, you can ask it to work harder, or you can try to iterate with follow up queries, corrections and refinements.

[Ai2 @allen_ai]

Meet Ai2 Paper Finder, an LLM-powered literature search system.

Searching for relevant work is a multi-step process that requires iteration. Paper Finder mimics this workflow — and helps researchers find more papers than ever 🔍

[Dan Bareket @dbreqt]

@DNVR_Nuggets nuggets have four of the top-ten 3pt shooters in the last five playoffs

[Dan Bareket @dbreqt]

@zamird91 יכול ללכת לקיבוץ גלויות לקחת 41

[Dan Bareket @dbreqt]

@eagereyes @yoavgo the saga continues

[Dan Bareket @dbreqt]

@yoavgo https://t.co/Wb644i91lN

[Dan Bareket @dbreqt]

@zehavoc @ArijRiabi @rtsarfaty Very happy to pass the torch :))

[Dan Bareket @dbreqt]

Ooh some great non-gold tokenization stuff from @ArijRiabi @zehavoc

https://t.co/bKJKjTxN6D

[Renana Keydar @RKeydar]

ICAIL 2023 has begun! 😀 tomorrow we open the lecture day with a joint law and NLP project with Eliya Habba @dbreqt @GabiStanovsky.

[Shauli Ravfogel @ravfogel]

Check out our new paper on mapping abstract descriptions to sentences! We prompt GPT3 to create a dataset of <sentence, description>, and use it to train a retrieval model. A joint work with @valentina__py , Amir DN Cohen, @AvshalomM and @yoavgo (1/6)
https://t.co/3e5bQByJAh

[Dan Bareket @dbreqt]

@yoavgo גם אני תהיתי, אבל מה שבטוח הוא מתפקד כאחלה תוף המוני

[Dan Bareket @dbreqt]

יאללה מחר כולם רואים ביחד 21 ג'אמפ סטריט ועושים שולם

[Dan Bareket @dbreqt]

@yoavgo ... אחרי חוק הנבצרות אין להם סמכות לדון בעניין

[Dan Bareket @dbreqt]

@yoavgo גלנט + התגובה של ביבי לבגץ שעכשיו

[Dan Bareket @dbreqt]

@yoavgo Well yea, shitty in every possible way, but still comparing the content of academic publishing to that of other media - things can get much much worse real easy

[Dan Bareket @dbreqt]

@yoavgo but importantly this was written pre-internet and (stupid) bibliometrics, when the intended audience of citations were readers and not calculated scores that disregard the citation context

[Dan Bareket @dbreqt]

@yoavgo I like the way Latour put it in Science in Action. The general strategy with citation: do whatever you can to render existing literature helpful to your claims; e.g. weaken your enemies, paralyze those you can't weaken, help your allies, support those who supply you resources

[Dan Bareket @dbreqt]

@yoavmatchulsky ברוך הבא למועדון