<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Sequence Models on Nalar</title>
    <link>https://nalar.dev/tags/sequence-models/</link>
    <description>Recent content in Sequence Models on Nalar</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 04 Sep 2026 00:00:00 +0700</lastBuildDate>
    <atom:link href="https://nalar.dev/tags/sequence-models/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Understand Teacher Forcing in Autoregressive Models</title>
      <link>https://nalar.dev/understand-teacher-forcing-in-autoregressive-models/</link>
      <pubDate>Fri, 04 Sep 2026 00:00:00 +0700</pubDate>
      <guid>https://nalar.dev/understand-teacher-forcing-in-autoregressive-models/</guid>
      <description>&lt;p&gt;An autoregressive model generates a sequence one element at a time. A language model predicts the next token from the tokens before it; a sequence model might similarly predict the next symbol, event, or value from an existing prefix.&lt;/p&gt;&#xA;&lt;p&gt;That creates a practical training question: when teaching the model to predict step 5, should the input contain the correct steps 1–4 from the dataset, or the model&amp;rsquo;s own earlier predictions?&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
