Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings

• URL: http://arxiv.org/abs/2405.16820v1
• Date: Mon, 27 May 2024 04:38:10 GMT
• Title: Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings
• Authors: Robert Wolfe, Isaac Slaughter, Bin Han, Bingbing Wen, Yiwei Yang, Lucas Rosenblatt, Bernease Herman, Eva Brown, Zening Qu, Nic Weber, Bill Howe,
• Abstract summary: We see for-profit closed-weight models as incompatible with requirements for transparency, privacy, adaptability, and standards of evidence. We assess the feasibility of using smaller, open-weight models to replace GPT-4-Turbo in zero-shot, few-shot, and fine-tuned regimes. We find that with relatively low effort, very low absolute monetary cost, and relatively little data for fine-tuning, small open-weight models can achieve competitive performance.
• Score: 11.878413021518194
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The rapid proliferation of generative AI has raised questions about the competitiveness of lower-parameter, locally tunable, open-weight models relative to high-parameter, API-guarded, closed-weight models in terms of performance, domain adaptation, cost, and generalization. Centering under-resourced yet risk-intolerant settings in government, research, and healthcare, we see for-profit closed-weight models as incompatible with requirements for transparency, privacy, adaptability, and standards of evidence. Yet the performance penalty in using open-weight models, especially in low-data and low-resource settings, is unclear. We assess the feasibility of using smaller, open-weight models to replace GPT-4-Turbo in zero-shot, few-shot, and fine-tuned regimes, assuming access to only a single, low-cost GPU. We assess value-sensitive issues around bias, privacy, and abstention on three additional tasks relevant to those topics. We find that with relatively low effort, very low absolute monetary cost, and relatively little data for fine-tuning, small open-weight models can achieve competitive performance in domain-adapted tasks without sacrificing generality. We then run experiments considering practical issues in bias, privacy, and hallucination risk, finding that open models offer several benefits over closed models. We intend this work as a case study in understanding the opportunity cost of reproducibility and transparency over for-profit state-of-the-art zero shot performance, finding this cost to be marginal under realistic settings.

Related papers

• Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research [0.0]
  Large Language Models (LLMs) are distinguished by their architecture, which dictates their parameter size and performance capabilities. Social scientists have increasingly adopted LLMs for text classification tasks, which are difficult to scale with human coders. This study demonstrates that small, fine-tuned open-source LLMs can achieve equal or superior performance to models such as ChatGPT-4.
  arXiv  Detail & Related papers  (2024-10-31T20:26:30Z)
• SLIM: Spuriousness Mitigation with Minimal Human Annotations [24.863960194779875]
  We introduce SLIM, a cost-effective and performance-targeted approach to reducing spurious correlations in deep learning. By prioritizing data quality over complicated training strategies, SLIM curates a smaller yet more feature-balanced data subset, fostering the development of spuriousness-robust models.
  arXiv  Detail & Related papers  (2024-07-08T04:15:44Z)
• Automated Text Scoring in the Age of Generative AI for the GPU-poor [49.1574468325115]
  We analyze the performance and efficiency of open-source, small-scale generative language models for automated text scoring. Results show that GLMs can be fine-tuned to achieve adequate, though not state-of-the-art, performance.
  arXiv  Detail & Related papers  (2024-07-02T01:17:01Z)
• Improving Large Models with Small models: Lower Costs and Better Performance [81.55672406002715]
  We propose Data Shunt$+$ (DS$+$), a general paradigm for collaboration of small and large models. 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 $31.18%$.
  arXiv  Detail & Related papers  (2024-06-15T14:44:43Z)
• Low-rank finetuning for LLMs: A fairness perspective [54.13240282850982]
  Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models. This paper investigates the effectiveness of these methods in capturing the shift of fine-tuning datasets from the initial pre-trained data distribution. We show that low-rank fine-tuning inadvertently preserves undesirable biases and toxic behaviors.
  arXiv  Detail & Related papers  (2024-05-28T20:43:53Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models [53.859446823312126]
  SoTA open source models of varying sizes from 7B - 65B, on average, improve 8.2% from their baseline performance. Strikingly, even models with extremely small memory footprints, such as Vicuna-7B, show a 11.74% improvement overall and up to a 25.39% improvement in high-creativity, open ended tasks.
  arXiv  Detail & Related papers  (2023-10-11T15:56:00Z)
• Fairness Reprogramming [42.65700878967251]
  We propose a new generic fairness learning paradigm, called FairReprogram, which incorporates the model reprogramming technique. Specifically, FairReprogram considers the case where models can not be changed and appends to the input a set of perturbations, called the fairness trigger. We show both theoretically and empirically that the fairness trigger can effectively obscure demographic biases in the output prediction of fixed ML models.
  arXiv  Detail & Related papers  (2022-09-21T09:37:00Z)
• Quantization for decentralized learning under subspace constraints [61.59416703323886]
  We consider decentralized optimization problems where agents have individual cost functions to minimize subject to subspace constraints. We propose and study an adaptive decentralized strategy where the agents employ differential randomized quantizers to compress their estimates. The analysis shows that, under some general conditions on the quantization noise, the strategy is stable both in terms of mean-square error and average bit rate.
  arXiv  Detail & Related papers  (2022-09-16T09:38:38Z)
• Promoting Fairness through Hyperparameter Optimization [4.479834103607383]
  This work explores, in the context of a real-world fraud detection application, the unfairness that emerges from traditional ML model development. We propose and evaluate fairness-aware variants of three popular HO algorithms: Fair Random Search, Fair TPE, and Fairband. We validate our approach on a real-world bank account opening fraud use case, as well as on three datasets from the fairness literature.
  arXiv  Detail & Related papers  (2021-03-23T17:36:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.