Pith. sign in

REVIEW 4 cited by

Synthesis of Mathematical programs from Natural Language Specifications

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

arxiv 2304.03287 v1 pith:42KGE4QM submitted 2023-03-30 cs.AI cs.CLcs.LG

classification cs.AIcs.CLcs.LG
keywords mathematicalbeamsprogramsaccuracycodet5executionlanguagemodeling
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Several decision problems that are encountered in various business domains can be modeled as mathematical programs, i.e. optimization problems. The process of conducting such modeling often requires the involvement of experts trained in operations research and advanced algorithms. Surprisingly, despite the significant advances in the methods for program and code synthesis, AutoML, learning to optimize etc., there has been little or no attention paid to automating the task of synthesizing mathematical programs. We imagine a scenario where the specifications for modeling, i.e. the objective and constraints are expressed in an unstructured form in natural language (NL) and the mathematical program has to be synthesized from such an NL specification. In this work we evaluate the efficacy of employing CodeT5 with data augmentation and post-processing of beams. We utilize GPT-3 with back translation for generation of synthetic examples. Further we apply rules of linear programming to score beams and correct beams based on common error patterns. We observe that with these enhancements CodeT5 base gives an execution accuracy of 0.73 which is significantly better than zero-shot execution accuracy of 0.41 by ChatGPT and 0.36 by Codex.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language

    cs.AI 2026-05 reject novelty 7.0 of 10

    Training an LLM as a multi-turn agent that runs and repairs solver code raises verified optimization solve rates, with the 4B PEARL model outperforming DeepSeek-V3.2-685B in aggregate.

  2. InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    InvEvolve evolves white-box inventory policies from LLMs with statistical safety guarantees and outperforms classical and deep learning methods on synthetic and real retail data.

  3. InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    InvEvolve uses LLMs and RL to generate certified inventory policies that outperform classical and deep learning methods on synthetic and real data while providing multi-period performance guarantees.

  4. InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    InvEvolve evolves inventory policies using LLMs with RL and provides statistical safety guarantees, outperforming classical and DL methods on synthetic and real data.

Pith tools