Pith. sign in

REVIEW 8 cited by

How Can Large Language Models Help Humans in Design and Manufacturing?

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 2307.14377 v1 pith:LTZLFRK6 submitted 2023-07-25 cs.CL cs.AI

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

The advancement of Large Language Models (LLMs), including GPT-4, provides exciting new opportunities for generative design. We investigate the application of this tool across the entire design and manufacturing workflow. Specifically, we scrutinize the utility of LLMs in tasks such as: converting a text-based prompt into a design specification, transforming a design into manufacturing instructions, producing a design space and design variations, computing the performance of a design, and searching for designs predicated on performance. Through a series of examples, we highlight both the benefits and the limitations of the current LLMs. By exposing these limitations, we aspire to catalyze the continued improvement and progression of these models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    CADBench is a new multimodal benchmark for CAD program generation that combines 18k samples from DeepCAD, Fusion 360, ABC, MCB, and Objaverse across clean/noisy meshes and various renders, used to test 11 models and r...

  2. Formalizing Linear Motion G-code for Invariant Checking and Differential Testing of Fabrication Tools

    cs.PL 2025-08 conditional novelty 7.0 of 10

    A new G-code lifting technique, representing linear motion as cuboids and approximate point clouds, enables invariant checking and differential testing of fabrication tools.

  3. Masked Topology Modeling for Self-Supervised Learning on Parametric CAD

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Masked Topology Modeling pretrains B-rep encoders by hiding face-adjacency edges and predicting their kernel-computed convexity and curve type, improving label efficiency on CAD benchmarks.

  4. CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation

    cs.CV 2026-05 conditional novelty 6.0 of 10

    CADBench is a multimodal benchmark for CAD program generation that shows specialized mesh-to-CAD models outperform general vision-language models but degrade with complexity and modality shifts.

  5. Foundation Models for Automatic CAD Generation

    cs.AI 2026-07 conditional novelty 5.0 of 10

    Top instruction-tuned LLMs generate watertight parametric CAD for four simple geometry families at ~99% mesh success under iterative analytic or VLM critique on a 97-problem benchmark.

  6. Enhancing Creativity in 3D Generative Design via a TRIZ-Inspired Text-to-CAD Framework

    cs.LG 2026-06 unverdicted novelty 4.0 of 10

    TRIZ-guided LLM prompting produces structurally diverse CAD chair variants with 4.0-14.7% mass reduction while preserving integrity in a two-stage pipeline.

  7. Human-in-the-Loop: Quantitative Evaluation of 3D Models Generation by Large Language Models

    cs.CV 2025-09 reject novelty 4.0 of 10

    Quantitative geometry scores across four input types show semantic richness improves LLM-generated CAD fidelity, with code-based prompts reaching perfect scores only after human code edits.

  8. Physics-informed generative AI for semiconductor manufacturing: Enforcing hard physical constraints in generative models by construction

    cs.LG 2026-06 unverdicted novelty 3.0 of 10

    Perspective arguing that physics-informed generative models enforcing hard constraints by construction outperform post-hoc filtering for semiconductor manufacturing and similar physical systems.

Pith tools