Log inSign up
user avatar
Nitay Calderon
@NitCal
Research Scientist @GoogleResearch | PhD @TechnionLive | NLP
nitaytech.github.io
Joined June 2022
781
Following
465
Followers
RepliesMedia
  • Pinned
    user avatar
    Nitay Calderon
    @NitCal
    Feb 24
    [1/7] Why do frontier LLMs make factual errors? Is it because they never learned the fact… or because they can’t access knowledge they already encoded? In our new paper, we show: The bottleneck is not encoding; it is recall. 🧵👇 Paper: arxiv.org/abs/2602.14080 Many thanks to
    Image
  • user avatar
    Nitay Calderon
    @NitCal
    May 15
    My advisor always says time is our most valuable resource, I tell students I teach/work with that I dont plan to spend more time reading something than the author spent writing it. I support arXiv's decision. Asking authors to polish AI-generated content is a *VERY* low bar.
    user avatar
    Thomas G. Dietterich
    @tdietterich
    May 14
    Attention @arxiv authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents were generated. 1/
  • user avatar
    Nitay Calderon
    @NitCal
    May 8
    If you care about knowledge in LLMs, and why parametric knowledge remains a fundamentally important research problem, you should read Gal’s tweet 🤯
    user avatar
    Gal Yona
    @_galyo
    May 8
    .@NitCal will be presenting "Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality" at ICML 2026 next month. (tl;dr: we show encoding is near-saturated on frontier LLMs, but models still struggle to recall encoded facts.) One recurring piece of
    Image
  • user avatar
    Nitay Calderon
    @NitCal
    May 4
    Our paper got accepted to @icmlconf! 🥳🥳 I also want to say a few warm words about the reviewers and AC. Maybe because our paper was under Policy A (LLM use is prohibited), but the review process felt unusually professional and refreshing, almost like a reminder of pre-2024
    user avatar
    Nitay Calderon
    @NitCal
    Feb 24
    [1/7] Why do frontier LLMs make factual errors? Is it because they never learned the fact… or because they can’t access knowledge they already encoded? In our new paper, we show: The bottleneck is not encoding; it is recall. 🧵👇 Paper: arxiv.org/abs/2602.14080 Many thanks to
    Image