MétaCan
Menu
Back to cohort
Record W4401783591 · doi:10.1080/03155986.2024.2388452

LM4OPT: Unveiling the potential of Large Language Models in formulating mathematical optimization problems

2024· article· en· W4401783591 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
venuePublished in a venue whose home country is Canada.

Bibliographic record

VenueINFOR Information Systems and Operational Research · 2024
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsQueen's University
Fundersnot available
KeywordsComprehensionTask (project management)Computer scienceShot (pellet)Natural language processingArtificial intelligenceMachine learningEngineeringChemistry

Abstract

fetched live from OpenAlex

In the fast-paced domain of natural language processing, converting linguistic descriptions into mathematical optimization problems is a complex task, requiring profound comprehension and processing skills from Large Language Models (LLMs). In this study, various LLMs were evaluated, including GPT-3.5, GPT-4, and smaller variants with seven billion parameters: Llama-2, Falcon, Mistral, and Zephyr. This research investigated their performance in both zero-shot and one-shot settings for this task, revealing that GPT-4 outperformed others, particularly in the one-shot scenario. A core contribution of this study is the development of LM4OPT, a progressive fine-tuning framework specifically designed for smaller LLMs. This framework leverages noisy embeddings and specialized datasets to enhance the performance of the models. Regardless of the inherent limitations of smaller models in processing complex and lengthy input contexts, our experimental results indicate a significant reduction in the performance disparity between smaller and larger models when the former are fine-tuned using LM4OPT. Our empirical study, utilizing the NL4Opt dataset, unveils that GPT-4 surpasses the baseline performance established by previous research, achieving an accuracy of 63.30%, solely based on the problem description in natural language, and without relying on any additional named entity information. GPT-3.5 follows closely, both outperforming the progressively fine-tuned smaller models.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.972
Threshold uncertainty score0.850

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.004
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.050
GPT teacher head0.345
Teacher spread0.295 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it