Sign in

Yanai Elazar

@yanai.bsky.social
2.5K followers 404 following 126 posts

Assistant Professor at Bar-Ilan University yanaiela.github.io

PostsRepliesMedia
Reposted by Yanai Elazar
Zeerak Talat زیرک طلعت (they/them) @zeerak.bsky.social · 12/06/2026
NLP reviews suck! But why is not clear– @aclrollingreview.bsky.social provides *a lot* of guidance for how to review, but in that, first principles get lost. So @adamlopez.bsky.social and I have written down some of our thoughts on first principles.
medium.com
The Missing First Principles of Reviewing for ACL
Zeerak Talat & Adam Lopez, University of Edinburgh
1236
Yanai Elazar @yanai.bsky.social · 27/05/2026
this 💯💯💯
030
Yanai Elazar @yanai.bsky.social · 14/04/2026
Are you interested in interning with me and my lab? A unique opportunity for a 4-month research stay, with generous funding as an Azrieli visiting PhD fellow! DM me if you're interested. azrielifoundation.org/fellows/visi...
azrielifoundation.org
International Visiting PhD Fellowship - The Azrieli Foundation
The Azrieli Fellows Program is an elite group of academics who cultivate a network of leading professionals in Israel and around the world.
020
Yanai Elazar @yanai.bsky.social · 17/03/2026
aww 🤗 @sarah-nlp.bsky.social
120
Yanai Elazar @yanai.bsky.social · 16/03/2026
Or the resolution of the papers by the authors themselves! www.bigpictureworkshop.com/2023/the-big... (link can be found on top)
bigpictureworkshop.com
Big Picture Workshop - The Big Picture 2023
News
150
Yanai Elazar @yanai.bsky.social · 16/03/2026
ACL is not an AI conference seems like a big one
010
Yanai Elazar @yanai.bsky.social · 15/03/2026
I've been playing hades 2 on my Mac recently, it's quite fun! Apparently it's coming to ps5 as well at some point. I think you'd appreciate the graphics
010
Yanai Elazar @yanai.bsky.social · 03/02/2026
Excited to have the Big Picture workshop back for another iteration this year at @aclmeeting.bsky.social Submit your big picture ideas, consolidation work, phd thesis distillation, etc. by March 5th! www.bigpictureworkshop.com w/ Allyson Ettinger, @norakassner.bsky.social, @sebruder.bsky.social
093
Yanai Elazar @yanai.bsky.social · 31/01/2026
But I guess this is where the "position" of our paper gets in. At least it wasn't rejected from arXiv 😂
000
Yanai Elazar @yanai.bsky.social · 31/01/2026
a) but not a reasonable one. there are many such papers, many good ones, and it's not like arXiv is this sanctuary of high-quality papers from the first place. I don't see why should we enforce this quasi appearance of quality suddenly. b) I don't think this is true anymore.
100
Yanai Elazar @yanai.bsky.social · 31/01/2026
correct! I combined them together here for brevity (some may say laziness. but in fact arXiv treats them the same, and so do we (at least we try, in our evaluations and instructions).
120
Yanai Elazar @yanai.bsky.social · 31/01/2026
Please read the paper. Percentages are far from the only metric to look at.
100
Yanai Elazar @yanai.bsky.social · 29/01/2026
Job application process in 2026: Applicant: I have written 3 papers Interviewer: where? Applicant: arXiv Interviewer: hired!
process.in
040
Yanai Elazar @yanai.bsky.social · 29/01/2026
No, we unfortunately couldn't get our hands on such data. But from our understanding such data (in the worse case scenario) shouldn't affect the trends we found in our results.
120
Reposted by Yanai Elazar
Maria Antoniak @mariaa.bsky.social · 29/01/2026
CS ArXiv recently banned “review and position” papers, but what are those? Do they include more generated content? Who is most affected by this change? @yanai.bsky.social and I dug into the data to find out! Nearly 50% of Computers & Society papers might be censored, vs 3% of Computer Vision ‼️
24319
Yanai Elazar @yanai.bsky.social · 29/01/2026
and lastly, a huge thanks to @pangram.com who provided us with credits to detect AI slop in scientific papers!
040
Yanai Elazar @yanai.bsky.social · 29/01/2026
It's been an absolute pleasure to work on this with @mariaa.bsky.social ! and I hope you find this interesting. Feedback is welcome! arxiv.org/abs/2601.17036
arxiv.org
LLM-Generated or Human-Written? Comparing Review and Non-Review Papers on ArXiv
ArXiv recently prohibited the upload of unpublished review papers to its servers in the Computer Science domain, citing a high prevalence of LLM-generated content in these categories. However, this de...
191
Yanai Elazar @yanai.bsky.social · 29/01/2026
In addition, when considering different subfields, we find striking differences in how we classify 'position' papers, leading to huge differences in how this policy affects different CS subfields.
160
Yanai Elazar @yanai.bsky.social · 29/01/2026
However! when considering the number of papers from each type, we find there are significantly more non-review papers that are LLM-generated in all categories (cs and physics in the first tweet, math and stats here). These results question the main motivation of this new policy.
150
Yanai Elazar @yanai.bsky.social · 29/01/2026
We then calculate the percentage of LLM-generated papers in each category, and find that indeed, 'position' papers have higher percentages of LLM-generated papers, across the past three years.
140
Yanai Elazar @yanai.bsky.social · 29/01/2026
We establish two classifiers that predict based on papers' abstracts* whether they are 'position' vs non-position papers, and whether they are LLM-generated, using two existing classifiers. We also experiment with classifying the full papers, and reach similar conclusions.
240
Yanai Elazar @yanai.bsky.social · 29/01/2026
In this new paper (w/ @mariaa.bsky.social ) we study these questions, and try to provide some answers. Overall, we find evidence that this decision does not make much sense, and that it should be reconsidered!
150
Yanai Elazar @yanai.bsky.social · 29/01/2026
However, they provided no empirical evidence to support this decision. How many LLM-generated papers are being posted on arXiv? How many position papers are posted on arXiv? Do these ratios justify this abrupt solution? What are 'review' papers anyway?
240
Yanai Elazar @yanai.bsky.social · 29/01/2026
🚨 New Study 🚨 @arxiv.bsky.social has recently decided to prohibit any 'position' paper from being submitted to its CS servers. Why? Because of the "AI slop", and allegedly higher ratios of LLM-generated content in review papers, compared to non-review papers.
2299
Yanai Elazar @yanai.bsky.social · 16/01/2026
Microsoft word wizard
010
Yanai Elazar @yanai.bsky.social · 16/01/2026
"at least it's not Linkedin!" - if that's not shitposting idk what is
130
Yanai Elazar @yanai.bsky.social · 05/01/2026
We'll see about that...
030
Yanai Elazar @yanai.bsky.social · 05/01/2026
I think I'm in a secret competition with my co-author about who uses more footnotes in the paper.
140
Yanai Elazar @yanai.bsky.social · 01/12/2025
Thanks! I've actually read it, and I feel like it falls mostly under the "for people who don't know how LLMs work" category, for which it can be super useful! But I'm looking for something else.
000
Yanai Elazar @yanai.bsky.social · 01/12/2025
Any good tutorials/guides on how to code with LLMs? What I found so far targeted folks who don't know what they are, mostly setting expectations and saying what LLMs can or cannot do. I'm beyond that. I'm looking for best practices. Kind of design patterns for vibe coding.
430
Yanai Elazar @yanai.bsky.social · 30/11/2025
A data point in favor is from an observational data study we performed on the effect of early arxiving (= potentially breaking anonymity) on paper acceptance. We measured very small effects, and perhaps more importantly, no difference in the effect on different groups. arxiv.org/abs/2306.13891
arxiv.org
Estimating the Causal Effect of Early ArXiving on Paper Acceptance
What is the effect of releasing a preprint of a paper before it is submitted for peer review? No randomized controlled trial has been conducted, so we turn to observational data to answer this questio...
010
Yanai Elazar @yanai.bsky.social · 13/11/2025
azrielifoundation.org/azrieli-fell...
azrielifoundation.org
Call for Applications for the Azrieli International Postdoctoral Fellowship-2026-27 - The Azrieli Foundation
000
Yanai Elazar @yanai.bsky.social · 13/11/2025
Interested in interpretability, data attribution, evaluation, and similar topics? Interested in doing a postdoc with me? Apply to the prestigious Azrieli program! Link below 👇 DMs are open (email is good too!)
151
Yanai Elazar @yanai.bsky.social · 25/10/2025
You had one job!
070
Yanai Elazar @yanai.bsky.social · 17/10/2025
would you like to have a pop tart?
110
Yanai Elazar @yanai.bsky.social · 13/10/2025
cool, let's have a chat then!
010
Yanai Elazar @yanai.bsky.social · 13/10/2025
and in another work led by @chantalsh.bsky.social we also found a convergence of LLMs to the same patterns (syntactic templates) arxiv.org/abs/2407.00211
arxiv.org
Detection and Measurement of Syntactic Templates in Generated Text
Recent work on evaluating the diversity of text generated by LLMs has focused on word-level features. Here we offer an analysis of syntactic features to characterize general repetition in models, beyo...
030
Yanai Elazar @yanai.bsky.social · 13/10/2025
Cool stuff! We had a (somewhat) similar investigation in text2image models where we actually found that newer models are becoming even less diverse arxiv.org/abs/2410.22592
arxiv.org
GRADE: Quantifying Sample Diversity in Text-to-Image Models
We introduce GRADE, an automatic method for quantifying sample diversity in text-to-image models. Our method leverages the world knowledge embedded in large language models and visual question-answeri...
250
Reposted by Yanai Elazar
Chantal @chantalsh.bsky.social · 24/09/2025
"AI slop" seems to be everywhere, but what exactly makes text feel like "slop"? In our new work (w/ @tuhinchakr.bsky.social, Diego Garcia-Olano, @byron.bsky.social ) we provide a systematic attempt at measuring AI "slop" in text! arxiv.org/abs/2509.19163 🧵 (1/7)
13317
Reposted by Yanai Elazar
Naomi Saphra @nsaphra.bsky.social · 24/09/2025
I did a QA with Quanta about interpretability and training dynamics! I got to talk about a bunch of research hobby horses and how I got into them.
26512
Yanai Elazar @yanai.bsky.social · 24/09/2025
the transparency is just so bad
100
Yanai Elazar @yanai.bsky.social · 24/09/2025
lol I was very confused towards the end until i read the title again
110
Yanai Elazar @yanai.bsky.social · 24/09/2025
The new Tahoe UI is so bad. Everything just looks so blurred...
110
Yanai Elazar @yanai.bsky.social · 18/09/2025
Interesting opportunity for a research visit through the Azrieli foundation - azrielifoundation.org/azrieli-fell... Let me know if you're interested!
azrielifoundation.org
Call for Applications for the Azrieli International Visiting PhD Fellowship - The Azrieli Foundation
The Azrieli International Visiting PhD Fellowship offers outstanding international PhD candidates the opportunity to conduct short-term research in Israel, fostering academic collaboration and strengt...
010
Yanai Elazar @yanai.bsky.social · 03/09/2025
Organizing a workshop? Checkout our compiled material for organizing one: www.bigpictureworkshop.com/open-workshop (and hopefully we'll be back for another iteration of the Big Picture next year w/ Allyson Ettinger, @norakassner.bsky.social, @sebruder.bsky.social)
bigpictureworkshop.com
Big Picture Workshop - Open Workshop
Open sourcing the workshop
0173
Yanai Elazar @yanai.bsky.social · 20/08/2025
Thank you!!! ☺️
010
Yanai Elazar @yanai.bsky.social · 19/08/2025
Thank you!! 😊
010
Yanai Elazar @yanai.bsky.social · 16/08/2025
Thank you Ana!! 😊
010
Yanai Elazar @yanai.bsky.social · 15/08/2025
Thanks! and so I've heard 😀
000
Yanai Elazar @yanai.bsky.social · 15/08/2025
Thank you! 😊
000