<?xml version="1.0" encoding="utf-8"?><feed xmlns="http://www.w3.org/2005/Atom" ><generator uri="https://jekyllrb.com/" version="3.10.0">Jekyll</generator><link href="https://alonj.github.io/feed.xml" rel="self" type="application/atom+xml" /><link href="https://alonj.github.io/" rel="alternate" type="text/html" /><updated>2025-10-23T02:11:32+00:00</updated><id>https://alonj.github.io/feed.xml</id><title type="html">Alon Jacoby</title><subtitle>PhD Student @ [UPenn (CogComp Group)](https://cogcomp.seas.upenn.edu/)</subtitle><author><name>Alon Jacoby</name><email></email></author><entry><title type="html">Same Task, More Tokens</title><link href="https://alonj.github.io/same-task,-more-tokens/" rel="alternate" type="text/html" title="Same Task, More Tokens" /><published>2024-08-01T00:00:00+00:00</published><updated>2024-08-01T00:00:00+00:00</updated><id>https://alonj.github.io/same-task,-more-tokens</id><content type="html" xml:base="https://alonj.github.io/same-task,-more-tokens/"><![CDATA[<h2 id="same-task-more-tokens-the-impact-of-input-length-on-the-reasoning-performance-of-large-language-models"><a href="https://aclanthology.org/2024.acl-long.818">Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models</a></h2>

<p>Levy M.*, <strong>Jacoby A.*</strong>, &amp; Goldberg Y.</p>

<h3 id="published-in-proceedings-of-the-62nd-annual-meeting-of-the-association-for-computational-linguistics-2024">Published in <em>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics</em>, 2024</h3>

<p>Analysis of the impact of input length on the reasoning performance of large language models, using new, simple tasks unseen during the training of the models.</p>

<p>* Equal contribution</p>

<ul>
  <li>Outstanding Paper Award at ACL 2024</li>
  <li>Oral Presentation at ACL 2024</li>
  <li>Flash Talk at Israel Data Science and AI Initiative 3rd Annual Conference</li>
</ul>]]></content><author><name>Alon Jacoby</name></author><summary type="html"><![CDATA[Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models]]></summary></entry></feed>