Pith. sign in

REVIEW 3 cited by

Improving Large Models with Small models: Lower Costs and Better Performance

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 2406.15471 v1 pith:Q5BNN2HY submitted 2024-06-15 cs.CL cs.AIcs.LG

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

Pretrained large models (PLMs), such as ChatGPT, have demonstrated remarkable performance across diverse tasks. However, the significant computational requirements of PLMs have discouraged most product teams from running or fine-tuning them. In such cases, to harness the exceptional performance of PLMs, one must rely on expensive APIs, thereby exacerbating the economic burden. Despite the overall inferior performance of small models, in specific distributions, they can achieve comparable or even superior results. Consequently, some input can be processed exclusively by small models. On the other hand, certain tasks can be broken down into multiple subtasks, some of which can be completed without powerful capabilities. Under these circumstances, small models can handle the simple subtasks, allowing large models to focus on challenging subtasks, thus improving the performance. We propose Data Shunt$^+$ (DS$^+$), a general paradigm for collaboration of small and large models. DS$^+$ not only substantially reduces the cost associated with querying large models but also effectively improves large models' performance. For instance, ChatGPT achieves an accuracy of $94.43\%$ on Amazon Product sentiment analysis, and DS$^+$ achieves an accuracy of $95.64\%$, while the cost has been reduced to only $31.18\%$. Besides, experiments also prove that the proposed collaborative-based paradigm can better inject specific task knowledge into PLMs compared to fine-tuning.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Structuring Radiology Reports: Challenging LLMs with Lightweight Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Fully finetuned T5 and BERT2BERT models match or beat prompt-adapted LLMs up to 70B parameters on radiology report structuring, at less than 1% of the inference cost.

  2. KKA: Improving Vision Anomaly Detection through Anomaly-related Knowledge from Large Language Models

    cs.CV 2025-02 conditional novelty 6.0 of 10

    KKA uses LLM-generated anomaly descriptions, text-to-image synthesis, and iterative selection of hard examples to improve unsupervised vision anomaly detectors.

  3. FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting

    cs.LG 2025-06 reject novelty 4.0 of 10

    A feature-adaptive meta-learning framework for few-shot time series forecasting reports large gains, but its evaluation uses one to nine test tasks per dataset, lacks error bars, and contains numerical and preprocessi...

Pith tools