Pith. sign in

REVIEW 6 cited by

LLM Performance Predictors are good initializers for Architecture Search

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2310.16712 v2 pith:HPDJPT4S submitted 2023-10-25 cs.CL

Ganesh Jawahar , Muhammad Abdul-Mageed , Laks V. S. Lakshmanan , Dujian Ding This is my paper · ORCID
classification cs.CL
keywords performancesearchllm-pppredictorsarchitecturearchitecturesbaselinehs-nas
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this work, we utilize Large Language Models (LLMs) for a novel use case: constructing Performance Predictors (PP) that estimate the performance of specific deep neural network architectures on downstream tasks. We create PP prompts for LLMs, comprising (i) role descriptions, (ii) instructions for the LLM, (iii) hyperparameter definitions, and (iv) demonstrations presenting sample architectures with efficiency metrics and `training from scratch' performance. In machine translation (MT) tasks, GPT-4 with our PP prompts (LLM-PP) achieves a SoTA mean absolute error and a slight degradation in rank correlation coefficient compared to baseline predictors. Additionally, we demonstrate that predictions from LLM-PP can be distilled to a compact regression model (LLM-Distill-PP), which surprisingly retains much of the performance of LLM-PP. This presents a cost-effective alternative for resource-intensive performance estimation. Specifically, for Neural Architecture Search (NAS), we introduce a Hybrid-Search algorithm (HS-NAS) employing LLM-Distill-PP for the initial search stages and reverting to the baseline predictor later. HS-NAS performs similarly to SoTA NAS, reducing search hours by approximately 50%, and in some cases, improving latency, GFLOPs, and model size. The code can be found at: https://github.com/UBC-NLP/llmas.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. "Explain, Don't Just Warn!" -- A Real-Time Framework for Generating Phishing Warnings with Contextual Cues

    cs.CR 2025-05 conditional novelty 6.0 of 10

    PhishXplain uses a local LLM to generate real-time phishing warnings with annotated screenshots and contextual explanations, and a user study found these warnings improved later phishing detection.

  2. Cognitive-YOLO: LLM-Driven Architecture Synthesis from First Principles of Data for Object Detection

    cs.CV 2025-12 reject novelty 5.0 of 10

    An LLM with retrieval-augmented generation synthesizes object-detection architectures directly from dataset meta-features; the resulting models are competitive with YOLOv11n but at 5.6–6.7M parameters, not the 1.9M st...

  3. CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge

    cs.AR 2025-06 conditional novelty 5.0 of 10

    CLONE combines generative pruning, LoRA adapters, a parameter-free Mixture-of-Experts router, and learning-based DVFS to make LLM inference on edge devices faster and more energy-efficient, claiming up to 11.92x speed...

  4. MLZero: A Multi-Agent System for End-to-end Machine Learning Automation

    cs.MA 2025-05 conditional novelty 5.0 of 10

    MLZero, an LLM-based multi-agent system with perception and dual memory, reports 92 percent success on a new 25-task multimodal AutoML benchmark and the best average rank on MLE-Bench Lite.

  5. EfficientLLM: Efficiency in Large Language Models

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A large-scale benchmark of LLM efficiency techniques finds that every method trades off one resource for another, with the best choice depending on model scale, task, and hardware.

  6. A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving

    cs.NE 2025-09 conditional novelty 4.0 of 10

    A literature survey that classifies LLM-based optimization research into modeling and solving, with solving divided into LLMs as optimizers, low-level components, and high-level managers.

Pith tools