Alain AIROM’s Post

A Ranking & Evaluation Framework For LLM Hallucinations 👌 👇 https://lnkd.in/dZxP_3u3

Abstraction and generalization about phenomenon, interactions, and causation are thought to be at the core of a theory. We do not regard a collection of facts, or knowledge of an individual fact or event, as theory. "Data are not theory" (Sutton and Staw 1995., p. 374), although data may form the foundation for theoretical development. - Shirley Gregor. THE NATURE OF THEORY IN INFORMATION SYSTEMS. MIS Quarterly Vol. 30 No. 3. pp. 611-642/September 2006.

15 minutes to everything you need to know about chunking Today, we invited Anton from ChromaDB to discuss their research on chunking, the nuances of recursive text splitters, and most importantly, how to analyze your data. check it out! https://lnkd.in/g5UU5iyx if you want to learn more about how to improve your rag, check out our free 6 day crash course https://lnkd.in/gSENwXEw

Looking to empower your RAGs-based LLM Pipeline, how about exploring Knowledge Graphs? 🤔📊 We explore Knowledge Graphs and their ability to empower LLM Pipelines by boosting their contextual understanding. Read more in our publication's latest blog! ✍🏼 🔗: https://lnkd.in/e5gw_6QU #llm #knowledgegraph #opensourcellms #developerpractices

Mischief Rule of Interpretation: An Analysis https://lnkd.in/dk5NjPw6

Great article: frequent mistakes people make in interpreting p-values, confidence intervals and statistical power and how to correctly interpret. Article 👇 https://t.co/uq1sdJVeeb

☠️☠️Numbers are written in a particular way to ensure uniformity, clarity, and ease of understanding across the world.🫨🫨 😬😬The shapes of numbers were designed to reflect angles in some interpretations✨✨ (e.g., the old theory suggests "1" has 1 angle, "2" has 2 angles, etc.)🤯🤯 😵💫😵💫The form of each digit and its arrangement ensures mathematical accuracy, readability, and global consistency in various fields like science, finance, and technology.🥵🥵

LLM Hallucination Index is the first open-source leaderboard to rank popular LLMs based on their hallucination score. ▪️ 3 task types: question & answer w/ and w/o RAG, and long-form text generation ▪️ Evaluated using 7 popular datasets Website: https://lnkd.in/e9_nuYKu

The blog is now live with comment boxes! My most recent post is a proof I found on the famous Basel problem. Many more posts to come :D https://lnkd.in/ebrhJMUv

I was going through my (paper) archives the other day, where I've collected a lot of information from various sources - pre-internet predominently - and found a cutting from a 1993 edition of New Scientist, titled 'How to foil an Assassin' authored by Jiri Kubie. At the time I found it to be extremely interesting, and from a completely different perspective than I was accustomed to - namely a non-tactical, purely-objective, mathematical-model. I managed to find an electronic version of it thankfully - better than a scan of the hardly pristine cuttings I have, and re-typing the article was out of the question! Here it is: https://lnkd.in/dYhD4BA8