Category Archives: LLM

Large Language Models as Optimizers

Posted on September 15, 2023 by decisionmanagementcommunity

The article with this title was published on Sep 7, 2023. “In this work, we propose Optimization by PROmpting (OPRO), a simple and effective approach to leverage large language models (LLMs) as optimizers, where the optimization task is described in … Continue reading →

Posted in Algortithms, LLM, Optimization | Leave a comment

Potential legal risks of Generative AI addressed by Microsoft Copilot

Posted on September 10, 2023 by decisionmanagementcommunity

Customers of generative AI tools are concerned about the risk of IP infringement claims if they use the produced output. This is understandable, given recent public inquiries by authors and artists regarding how their own work is being used in … Continue reading →

Posted in Artificial Intelligence, LLM | Leave a comment

LLMs and ChatGPT at the Upcoming DecisionCAMP

Posted on September 6, 2023 by decisionmanagementcommunity

Large Language Models (LLMs) and ChatGPT will be well-presented at the upcoming DecisionCAMP-2023 on Sep 18-20. Here are a few examples: The very first presentation by Gary Hallmark will demonstrate the use of ChatGPT to generate all of the decision … Continue reading →

Posted in ChatGPT, Decision Modeling, LLM | Leave a comment

Paying for training data?

Posted on August 1, 2023 by decisionmanagementcommunity

“There are already a bunch of lawsuits from people who think their work may be in LLM training data, and now IAC and a group of publishers are apparently thinking about demanding some very large ($bn) payments. Unlike the ‘link … Continue reading →

Posted in ChatGPT, LLM | Leave a comment

Avoiding AI Hallucinations

Posted on July 30, 2023 by decisionmanagementcommunity

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 … Continue reading →

Posted in Artificial Intelligence, Knowledge Representation, LLM | Leave a comment

Combining Symbolic AI with LLMs

Posted on July 22, 2023 by decisionmanagementcommunity

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 … Continue reading →

Posted in Artificial Intelligence, LLM, Logic and AI, Rule Engines and BRMS | 1 Comment

Towards Programming as Conversation

Posted on June 13, 2023 by decisionmanagementcommunity

With LLMs taking the world, the prediction “What comes after serverless? Conversational Programming!” becomes a reality. It is interesting that even in 1967 Marvin Minsky understood the possibility of a 2-way conversation between programmer and computer, where the program is … Continue reading →

Posted in Human-Machine Interaction, LLM, Microservices, Software Development, Trends | Leave a comment

About LLM Reasoning and Planning Abilities

Posted on June 12, 2023 by decisionmanagementcommunity

Today Yann LeCun wrote: “Auto-regressive LLM have very limited reasoning and planning abilities. I do not believe we can get anywhere close to human-level AI (even cat-level AI) without (1) learning world models from sensory inputs like video, (2) an … Continue reading →

Posted in Artificial Intelligence, LLM, Optimization, Reasoning | Leave a comment

Combining LLM with Traditional Coding

Posted on June 10, 2023 by decisionmanagementcommunity

A project lead of Google Bard just announced that “Bard is improving at mathematical tasks, coding questions and string manipulation through a new technique called implicit code execution. Plus, it has a new export action to Google Sheets… With this … Continue reading →

Posted in Artificial Intelligence, Decision Intelligence, Human Intelligence, LLM | Leave a comment

Consistency Checks of Large Language Models

Posted on May 30, 2023 by decisionmanagementcommunity

Do Language Models Know When They’re Hallucinating References? Current state-of-the-art language models (LMs) are notorious for generating text with “hallucinations,” a primary example being book and paper references that lack any solid basis in their training data. However, we find … Continue reading →

Posted in Artificial Intelligence, ChatGPT, LLM | Leave a comment