<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM Techniques on English AI Terms Dictionary</title><link>https://terms-en.ai-term-hub.com/en/tags/llm-techniques/</link><description>Recent content in LLM Techniques on English AI Terms Dictionary</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 18 Jul 2026 11:44:44 +0000</lastBuildDate><atom:link href="https://terms-en.ai-term-hub.com/en/tags/llm-techniques/index.xml" rel="self" type="application/rss+xml"/><item><title>Chain-of-Thought Prompting</title><link>https://terms-en.ai-term-hub.com/en/terms/chain_of_thought_prompting/</link><pubDate>Sat, 18 Jul 2026 09:40:12 +0000</pubDate><guid>https://terms-en.ai-term-hub.com/en/terms/chain_of_thought_prompting/</guid><description>&lt;h2 id="definition">Definition&lt;/h2>
&lt;p>Chain-of-Thought (CoT) prompting improves the performance of large language models on complex reasoning tasks by explicitly asking the model to articulate its step-by-step logic. Instead of jumping directly to a conclusion, the model generates intermediate sentences that represent its thought process. This approach mimics human problem-solving strategies, significantly enhancing accuracy in mathematics, logic puzzles, and multi-step deductions. It can be implemented via few-shot examples or simple instructions like &amp;lsquo;Let&amp;rsquo;s think step by step.&amp;rsquo;&lt;/p></description></item><item><title>In-Context Learning</title><link>https://terms-en.ai-term-hub.com/en/terms/in_context_learning/</link><pubDate>Sat, 18 Jul 2026 07:39:00 +0000</pubDate><guid>https://terms-en.ai-term-hub.com/en/terms/in_context_learning/</guid><description>&lt;h2 id="definition">Definition&lt;/h2>
&lt;p>In-context learning (ICL) allows large language models to adapt to new tasks without updating their weights. By providing input-output pairs within the prompt context, the model infers the pattern and applies it to new queries. This zero-shot or few-shot capability enables rapid prototyping and flexibility, serving as a powerful alternative to traditional fine-tuning for tasks requiring quick adaptation to novel domains.&lt;/p>
&lt;h3 id="summary">Summary&lt;/h3>
&lt;p>A technique where models learn to perform tasks by observing examples provided in the prompt.&lt;/p></description></item></channel></rss>