<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project · HackerPapers discussions</title><link>https://hackerpaper.kaipfister.de/p/1909.01958/</link><description>Collected HN comments and submissions linking this paper.</description><language>en</language><lastBuildDate>Mon, 02 Nov 2026 11:16:22 GMT</lastBuildDate><atom:link href="https://hackerpaper.kaipfister.de/p/1909.01958/feed.xml" rel="self" type="application/rss+xml" /><item><title>From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project — mentioned by MacsHeadroom</title><link>https://news.ycombinator.com/item?id=35352214</link><guid isPermaLink="false">urn:hackerpapers:mention:1909.01958:35352214</guid><pubDate>Wed, 29 Mar 2023 03:52:18 GMT</pubDate><description>&lt;p&gt;I don&amp;#x27;t understand what you want me to ask it about. So I asked it something, as usual every citation and URL is real despite not having internet access or training data after 2021: &amp;lt;PROMPT&amp;gt;List some citations of recent Machine Learning papers discussing reasoning ability in Machine Learning Models such as HellaSwag. [REPLY]&amp;quot; As of my knowledge cutoff in September 2021, I can provide you with some citations for ML papers that discuss reasoning abilities in models and datasets like HellaSwag. However, you may want to search for more recent papers using a platform like arXiv or Google Scholar.…&lt;/p&gt;&lt;p&gt;&lt;a href="https://hackerpaper.kaipfister.de/p/1909.01958/"&gt;Paper and discussion history&lt;/a&gt;. A mention is not an endorsement.&lt;/p&gt;</description><category>cs.CL</category></item><item><title>From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project — mentioned by FiberBundle</title><link>https://news.ycombinator.com/item?id=24181347</link><guid isPermaLink="false">urn:hackerpapers:mention:1909.01958:24181347</guid><pubDate>Sun, 16 Aug 2020 21:10:25 GMT</pubDate><description>&lt;p&gt;I found the science exams results interesting and skimmed the paper [1]. They report an accuracy of &amp;gt;90% on the questions. What I found puzzling was that they have a section in the experimental results part where they test the robustness of the results using adverserial answer options, more specifically they used some simple heuristic to choose 4 additional answer options from the set of other questions which maximized &amp;#x27;confusion&amp;#x27; for the model. This resulted in a drop of more than 40 percentage points in the accuracy of the model. I find this extremely puzzling, what do these models actually…&lt;/p&gt;&lt;p&gt;&lt;a href="https://hackerpaper.kaipfister.de/p/1909.01958/"&gt;Paper and discussion history&lt;/a&gt;. A mention is not an endorsement.&lt;/p&gt;</description><category>cs.CL</category></item><item><title>From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project — HN submission</title><link>https://news.ycombinator.com/item?id=21019421</link><guid isPermaLink="false">urn:hackerpapers:submission:1909.01958:21019421</guid><pubDate>Thu, 19 Sep 2019 18:58:55 GMT</pubDate><description>&lt;p&gt;From F to A on the N.Y. Regents Science Exams: An Overview of Aristo Project&lt;/p&gt;&lt;p&gt;&lt;/p&gt;&lt;p&gt;2 points; 0 discussion replies on HN. &lt;a href="https://hackerpaper.kaipfister.de/p/1909.01958/"&gt;Paper and source history&lt;/a&gt;. A submission is not an endorsement.&lt;/p&gt;</description><category>cs.CL</category></item><item><title>From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project — HN submission</title><link>https://news.ycombinator.com/item?id=20886248</link><guid isPermaLink="false">urn:hackerpapers:submission:1909.01958:20886248</guid><pubDate>Thu, 05 Sep 2019 13:05:47 GMT</pubDate><description>&lt;p&gt;From &amp;#x27;F&amp;#x27; to &amp;#x27;A&amp;#x27; on the N.Y. Regents Science Exams: The Aristo Project&lt;/p&gt;&lt;p&gt;&lt;/p&gt;&lt;p&gt;1 point; 1 discussion reply on HN. &lt;a href="https://hackerpaper.kaipfister.de/p/1909.01958/"&gt;Paper and source history&lt;/a&gt;. A submission is not an endorsement.&lt;/p&gt;</description><category>cs.CL</category></item></channel></rss>
