Dear Xiaocheng,
thank you very much for your important and stimulating post! I have learned a lot from it.
The phrase "Everything is leaf" (,,Alles ist Blatt") goes back to the famous poet, thinker, and researcher Johann Wolfgang von Goethe. In his native language, German, ,,Blatt" ("leaf") is used not only in a botanical or even entomological- or ichthyological-zoological sense, but also for a sheet of paper, such as in a book. This is fitting, if only because the word "book" goes back to the tree "beech" (,,Buche"). Indeed, everything is represented in words, even in spiritual words, such as God's Word and the Book of Life, and words, in turn, consist of letters, in German: ,,Buchstaben" (from ,,Buch" ("book", "Fagus") and ,,Staben" ("staffs"), probably with etymological reasons in a Germanic cult of casting the lot).
Of course, a book is more than the sum of its pages (,,Blätter"), more than the sum of its words, and more than the sum of its letters, but also, quite essentially, of the connections between all of these, the meanings of all of these, ultimately the spirit underlying, in and above all of these, and the life or generalized life in all of these.
Ultimately, we also speak of the Holy Spirit and Eternal Life. All of these permeate and are simultaneously reflected through "language" in general or "languages" in particular.
It is therefore only logical that we trace our sciences and their applications back to languages and their mutual intelligibility and interactions. Artificial Intelligence (AI), especially Large Language Model (LLM) tools, is no exception. The latter are crucial for the development, deployment and management of LLMs in so many modern applications.
LLM tools serve tasks such as model fine-tuning and deployment, integration - including with other systems - and monitoring. Furthermore, they increase efficiency, align or streamline workflows, and enable the (generalized) creation of high-performance and more trustworthy uses of high-quality AI.
The various translation programs for and between, about, and to languages serve as a prototype or archetype for AI in general and LLM tools in particular. At the same time, we always keep in mind all the generalizations of all the aforementioned.
The (Holy) Spirit of truth, of life-friendliness and of love itself, which can and should be present in all of this, may then also be of decisive help in overcoming existing problems in LLM tools and in AI in general.
Reference: G.-W. Weber, Times and Lives, in completion.
------------------------------
Gerhard-Wilhelm Weber
Professor
Poznan University of Technology
Poznan
------------------------------
Original Message:
Sent: 06-24-2025 08:29
From: Xiaocheng Li
Subject: Capacity of LLMs in Doing OR/MS Research
Hi everyone,
We made a blog post here summarizing our findings in using ChatGPT-o3 for doing OR/MS research: The Capacity of LLMs in Doing OR/MS Research
A summary of the post is as follows:
- In this post, we provide a summary of our findings in exploring the capability of ChatGPT-o3 (accessible with $20/month Plus plan) model by OpenAI in doing OR/MS research. Based on our exploration, all research types within the INFORMS community will be affected by the LLM tools: theory, modeling, and empirical. The tools significantly change the way people do OR/MS research or other related fields like statistics. Beyond that, a rethinking of the values of doing research and the training of Ph.D. students is also necessary.
- The LLMs can help with every step of doing OR/MS research: proposing ideas, literature review, writing code, theory analysis/proof, and handling revisions. We don't try to argue for the failure case that the current LLMs can't do or to predict what the LLMs can do in the future. It's easy to find cases where the current LLMs fail or hallucinate. But we should keep in mind that the models are currently improved on a monthly/quarterly basis. We, as the authors of this article, wouldn't be surprised if a much stronger model appears in the next half or 1-2 years.
- The current LLM tools can pose a challenge to the current publication system of INFORMS, in terms of submission volume, review system, judgment criteria, etc. We don't have an estimate of how many researchers in the INFORMS community have already used these tools in doing research or writing reviews, or to what extent the current usage is. We want to take this opportunity to align the understanding of the matter across the whole community.
Cheers,
Xiaocheng
------------------------------
Xiaocheng Li
Assistant Professor
Imperial College Business School, Imperial College London
------------------------------