REVIEW 5 cited by
DualSchool: How Reliable are LLMs for Optimization Education?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
DualSchool: How Reliable are LLMs for Optimization Education?
read the original abstract
Consider the following task taught in introductory optimization courses which addresses challenges articulated by the community at the intersection of (generative) AI and OR: generate the dual of a linear program. LLMs, being trained at web-scale, have the conversion process and many instances of Primal to Dual Conversion (P2DC) at their disposal. Students may thus reasonably expect that LLMs would perform well on the P2DC task. To assess this expectation, this paper introduces DualSchool, a comprehensive framework for generating and verifying P2DC instances. The verification procedure of DualSchool uses the Canonical Graph Edit Distance, going well beyond existing evaluation methods for optimization models, which exhibit many false positives and negatives when applied to P2DC. Experiments performed by DualSchool reveal interesting findings. Although LLMs can recite the conversion procedure accurately, state-of-the-art open LLMs fail to consistently produce correct duals. This finding holds even for the smallest two-variable instances and for derivative tasks, such as correctness, verification, and error classification. The paper also discusses the implications for educators, students, and the development of large reasoning systems.
Forward citations
Cited by 5 Pith papers
-
Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
A sound, threshold-free battery of optimization-theoretic tests can catch unfaithful LLM-generated MILP models while never flagging faithful ones, and provably cannot catch certain error classes.
-
Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
LLM agent translates user prompts into model patches and selects primal-aware re-optimization techniques for large-scale dynamic problems, shown on supply-chain and exam-scheduling cases.
-
LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection
LISTEN is an agentic LLM framework for multi-objective selection using natural language, with LISTEN-U refining a parametric utility function and LISTEN-T performing tournament-style batch selections, showing context-...
-
LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection
LISTEN uses LLMs as zero-shot preference oracles, via iterative utility refinement (LISTEN-U) or tournament comparisons (LISTEN-T), to select preferred items from large multi-objective candidate sets.
-
Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
An LLM agent converts user prompts into optimization-model patches and selects primal-based re-optimization methods from a toolbox to produce feasible solutions for dynamic supply-chain and exam-scheduling problems.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.