<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Large Language Models | Mohammed Khalilia (محمد عبد الستار قاسم)</title><link>http://mohammedkhalilia.com/tags/large-language-models/</link><atom:link href="http://mohammedkhalilia.com/tags/large-language-models/index.xml" rel="self" type="application/rss+xml"/><description>Large Language Models</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sat, 11 Jan 2025 00:00:00 +0000</lastBuildDate><image><url>http://mohammedkhalilia.com/media/icon_hu_e7e672982174d01f.png</url><title>Large Language Models</title><link>http://mohammedkhalilia.com/tags/large-language-models/</link></image><item><title>Synthetic Panels</title><link>http://mohammedkhalilia.com/projects/synthetic-panels/</link><pubDate>Sat, 11 Jan 2025 00:00:00 +0000</pubDate><guid>http://mohammedkhalilia.com/projects/synthetic-panels/</guid><description>&lt;p&gt;Normally, the online panels follow the steps outlines in the figure below. Recruiting the right participants for a study can be difficult. You may not get the exact demographics you need, and the shorter the deadline, the less sure you can be that everyone will answer on time. One possible solution can be to use synthetic panels.&lt;/p&gt;
&lt;p&gt;
&lt;figure &gt;
&lt;div class="flex justify-center "&gt;
&lt;div class="w-full" &gt;
&lt;img alt="alt"
srcset="http://mohammedkhalilia.com/projects/synthetic-panels/synthetic_panel_human_hu_13f8adaa8d3d0ebc.webp 320w, http://mohammedkhalilia.com/projects/synthetic-panels/synthetic_panel_human_hu_db8541c5dd9600e3.webp 480w, http://mohammedkhalilia.com/projects/synthetic-panels/synthetic_panel_human_hu_791f81da70d7fbb.webp 760w"
sizes="(max-width: 480px) 100vw, (max-width: 768px) 90vw, (max-width: 1024px) 80vw, 760px"
src="http://mohammedkhalilia.com/projects/synthetic-panels/synthetic_panel_human_hu_13f8adaa8d3d0ebc.webp"
width="760"
height="239"
loading="lazy" data-zoomable /&gt;&lt;/div&gt;
&lt;/div&gt;&lt;/figure&gt;
&lt;/p&gt;
&lt;p&gt;Synthetic panels are powered by a first party proprietary AI model developed here at Qualtrics. Our synthetic panel is trained on thousands of responses from a variety of demographic backgrounds in order to more accurately predict how certain populations would respond to a survey.&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Trained on over 10 billions tokens.&lt;/li&gt;
&lt;li&gt;Completed training on 8 days.&lt;/li&gt;
&lt;li&gt;Utilized 32 A100 GPUs&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;The goal is to augment the human participants with the synthetic participants to fill in missing population segments and reduce recruitment time.&lt;/p&gt;
&lt;p&gt;
&lt;figure &gt;
&lt;div class="flex justify-center "&gt;
&lt;div class="w-full" &gt;
&lt;img alt="alt"
srcset="http://mohammedkhalilia.com/projects/synthetic-panels/synthetic_panel_ai_hu_277d2a3eeb10c934.webp 320w, http://mohammedkhalilia.com/projects/synthetic-panels/synthetic_panel_ai_hu_e2c25b5aae55d4e8.webp 480w, http://mohammedkhalilia.com/projects/synthetic-panels/synthetic_panel_ai_hu_f5047b8c190ece30.webp 760w"
sizes="(max-width: 480px) 100vw, (max-width: 768px) 90vw, (max-width: 1024px) 80vw, 760px"
src="http://mohammedkhalilia.com/projects/synthetic-panels/synthetic_panel_ai_hu_277d2a3eeb10c934.webp"
width="760"
height="239"
loading="lazy" data-zoomable /&gt;&lt;/div&gt;
&lt;/div&gt;&lt;/figure&gt;
&lt;/p&gt;
&lt;p&gt;A short demo of the synthic panel can be found below. Note this is an edited version of the
.
&lt;div style="position: relative; padding-bottom: 56.25%; height: 0; overflow: hidden;"&gt;
&lt;iframe allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share; fullscreen" loading="eager" referrerpolicy="strict-origin-when-cross-origin" src="https://www.youtube.com/embed/fMCuGQCZnek?autoplay=0&amp;amp;controls=1&amp;amp;end=0&amp;amp;loop=0&amp;amp;mute=0&amp;amp;start=0" style="position: absolute; top: 0; left: 0; width: 100%; height: 100%; border:0;" title="YouTube video"&gt;&lt;/iframe&gt;
&lt;/div&gt;
&lt;/p&gt;</description></item><item><title>Insight Explorer</title><link>http://mohammedkhalilia.com/projects/insight-explorer/</link><pubDate>Thu, 11 Jan 2024 00:00:00 +0000</pubDate><guid>http://mohammedkhalilia.com/projects/insight-explorer/</guid><description>&lt;p&gt;Insights Explorer is an AI-powered text analytics tool that uses your open-ended feedback to identify top themes, create headlines, and generate helpful summaries. This feature can help you understand large text datasets faster than ever, and is a great starting point for analysts working with unstructured feedback data.&lt;/p&gt;
&lt;p&gt;Any type of project with open text fields can be used for generating insights. That includes:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Survey projects&lt;/li&gt;
&lt;li&gt;Imported Data projects&lt;/li&gt;
&lt;li&gt;CX Dashboards&lt;/li&gt;
&lt;li&gt;Engagement&lt;/li&gt;
&lt;li&gt;Lifecycle&lt;/li&gt;
&lt;li&gt;Ad Hoc Employee Research&lt;/li&gt;
&lt;li&gt;Ticket Datasets&lt;/li&gt;
&lt;li&gt;XM Discover projects&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;
&lt;figure &gt;
&lt;div class="flex justify-center "&gt;
&lt;div class="w-full" &gt;
&lt;img alt="alt"
srcset="http://mohammedkhalilia.com/projects/insight-explorer/example_insight_explorer_hu_affd3e02f9660248.webp 320w, http://mohammedkhalilia.com/projects/insight-explorer/example_insight_explorer_hu_11388a65596469df.webp 480w, http://mohammedkhalilia.com/projects/insight-explorer/example_insight_explorer_hu_216a465cc4b7bada.webp 760w"
sizes="(max-width: 480px) 100vw, (max-width: 768px) 90vw, (max-width: 1024px) 80vw, 760px"
src="http://mohammedkhalilia.com/projects/insight-explorer/example_insight_explorer_hu_affd3e02f9660248.webp"
width="760"
height="465"
loading="lazy" data-zoomable /&gt;&lt;/div&gt;
&lt;/div&gt;&lt;/figure&gt;
&lt;/p&gt;</description></item></channel></rss>