Large language models (LLMs) trained on stale, incomplete information are prone to “hallucinations”—incorrect results, from slightly off-base to totally incoherent. Hallucinations include incorrect answers to questions and false information about people and events. This article “Why knowledge management is foundational to AI success” discussed how providing the right context to AI can improve accuracy and reduce hallucinations. Link
Continue reading
Dr. Walid Saba makes a compelling case for combining #symbolic #AI with the strengths of large language models. The limitations of current #LLMs are well articulated, especially the lack of explainability and failures in intentional contexts. Moving to a symbolic system could address these issues. His paper makes a compelling argument and outlines an original approach to move toward symbolic, #explainable LLMs. Expanding the reverse engineering analysis and testing the ideas on broader linguistic phenomena would be interesting next steps. The vision of combining strengths of modern AI with symbolic #representations is thought-provoking. Link
DecisionCAMP is the most popular annual event for Decision Management practitioners. It started in 2008 as October RulesFest, continued in 2009-2011 as RulesFest, became IntelliFest in 2012, and DecisionCAMP since 2013. See the entire history with various links to presentations, blog notes, etc.
This year DecisionCAMP will be held online on Sep 18-20. It is interesting to refresh the information from the latest camps and compare it with what to expect in 2023:
I’ve collected photos from different camps: enjoy good memories!
Continue reading
AI4OPT, NSF Artificial Intelligence Research Institute for Advances in Optimization, aims at delivering a paradigm shift in automated decision making at massive scales by fusing AI and Mathematical Optimization, to deliver breakthroughs that neither field can achieve independently. The Institute is driven by societal challenges in energy, supply chains, sustainability, and chip design and manufacturing. It fuses AI and Optimization, inspired by end-use cases in supply chains, energy systems, chip design and manufacturing, and sustainable food systems. Link
In Jan-2017 Mike Gualtieri from Forrester published a report “Prescriptive Analytics: The Black Belt Of Digital Decisions” which tied Analytics to actionable Decisions. Mike wrote: “Enterprises must stop wasting time and money on unactionable analytics. These efforts don’t matter if the resulting analytics don’t lead to better insights and decisions that are specifically linked to measurable business outcomes.” Since then the term “prescriptive analytics” was replaced with “Decision Intelligence” but the listed technologies became even more important today:
In the real world not all rules can be satisfied and we may consider them as preferences. For example, our June-2023 Challenge “Miss Manners” used well-tuned data with equal numbers of males and females at each party. Of course, real data is not like this, but we still want to help Miss Manners to seat all guests while sticking to her rules as much as possible. So, the seating arrangement “boy-girl-boy-girl and each guest has someone on the left or right with a common hobby” becomes not a Rule but a Preference. Let’s see how modern decision intelligence tools can address this advanced version of the notorious “Miss Manners” benchmark. Link
Bruce Silver published the latest news in the DMN standard including:
DecisionCAMP-2023 Program and Schedule are now available! This major annual Decision Management event will feature 19 interesting presentations from well-known and new presenters in the area of Decision Intelligence. They will cover many hot topics such as the common use of LLM and Rule Engines, Declarative Decision Modeling, Decision Testing and Explanations, Knowledge Representation, Decision Optimization, and real-world use cases. You may register for free now. Link
The Guardian: Two US lawyers fined for submitting fake court citations from ChatGPT. A law firm also penalized after chatbot invented six legal cases that were then used in an aviation injury claim. Link
Business Rules Manifesto is 20 years old and “it is as fresh as the day it was written. Only 2 pages, free, and translated into 18 languages, the Business Rules Manifesto ushered in a whole new way of thinking about business problems and automated solutions. With the emerging need for AI guardrails, as well as now a far more mature view of agile, more relevant than ever,” – says Ron Ross. Link
Decision Management Community 
You must be logged in to post a comment.