Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production

• URL: http://arxiv.org/abs/2312.14972v3
• Date: Tue, 16 Apr 2024 19:35:53 GMT
• Title: Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI's LLM with Open Source SLMs in Production
• Authors: Chandra Irugalbandara, Ashish Mahendra, Roland Daynauth, Tharuka Kasthuri Arachchige, Jayanaka Dantanarayana, Krisztian Flautner, Lingjia Tang, Yiping Kang, Jason Mars,
• Abstract summary: Many companies use large language models (LLMs) offered as a service, like OpenAI's GPT-4, to create AI-enabled product experiences. At the same time, a flurry of open-source small language models (SLMs) has been made available for commercial use. This paper presents a systematic evaluation methodology and a characterization of modern open-source SLMs.
• Score: 3.41402911469979
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Many companies use large language models (LLMs) offered as a service, like OpenAI's GPT-4, to create AI-enabled product experiences. Along with the benefits of ease-of-use and shortened time-to-solution, this reliance on proprietary services has downsides in model control, performance reliability, uptime predictability, and cost. At the same time, a flurry of open-source small language models (SLMs) has been made available for commercial use. However, their readiness to replace existing capabilities remains unclear, and a systematic approach to holistically evaluate these SLMs is not readily available. This paper presents a systematic evaluation methodology and a characterization of modern open-source SLMs and their trade-offs when replacing proprietary LLMs for a real-world product feature. We have designed SLaM, an open-source automated analysis tool that enables the quantitative and qualitative testing of product features utilizing arbitrary SLMs. Using SLaM, we examine the quality and performance characteristics of modern SLMs relative to an existing customer-facing implementation using the OpenAI GPT-4 API. Across 9 SLMs and their 29 variants, we observe that SLMs provide competitive results, significant performance consistency improvements, and a cost reduction of 5x~29x when compared to GPT-4.

Related papers

• EasyJudge: an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs [6.179084469089114]
  This paper presents EasyJudge, a model developed to evaluate significant language model responses. It is lightweight, precise, efficient, and user-friendly, featuring an intuitive visualization interface for ease of deployment and use.
  arXiv  Detail & Related papers  (2024-10-13T08:24:12Z)
• RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness [94.03511733306296]
  We introduce RLAIF-V, a framework that aligns MLLMs in a fully open-source paradigm for super GPT-4V trustworthiness. RLAIF-V maximally exploits the open-source feedback from two perspectives, including high-quality feedback data and online feedback learning algorithm. Experiments show that RLAIF-V substantially enhances the trustworthiness of models without sacrificing performance on other tasks.
  arXiv  Detail & Related papers  (2024-05-27T14:37:01Z)
• SMART: Automatically Scaling Down Language Models with Accuracy Guarantees for Reduced Processing Fees [21.801053526411415]
  Large Language Models (LLMs) have significantly boosted performance in natural language processing (NLP) tasks. The deployment of high-performance LLMs incurs substantial costs, primarily due to the increased number of parameters aimed at enhancing model performance. We introduce SMART, a novel framework designed to minimize the inference costs of NLP tasks while ensuring sufficient result quality.
  arXiv  Detail & Related papers  (2024-03-11T17:45:47Z)
• LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error [54.954211216847135]
  Existing large language models (LLMs) only reach a correctness rate in the range of 30% to 60%. We propose a biologically inspired method for tool-augmented LLMs, simulated trial and error (STE) STE orchestrates three key mechanisms for successful tool use behaviors in the biological system: trial and error, imagination, and memory.
  arXiv  Detail & Related papers  (2024-03-07T18:50:51Z)
• Towards Optimizing the Costs of LLM Usage [4.032848774697859]
  We study optimization problems trading off the quality and costs, both theoretically and empirically. We propose several deterministics for reducing tokens in a quality aware manner. Our methods reduce costs by 40%- 90% while improving quality by 4%-7%.
  arXiv  Detail & Related papers  (2024-01-29T16:36:31Z)
• From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities [111.44485171421535]
  We study the generalizability, trustworthiness, and causal reasoning capabilities of recent proprietary and open-source MLLMs across four modalities. We believe these properties are several representative factors that define the reliability of MLLMs. We uncover 14 empirical findings that are useful to understand the capabilities and limitations of both proprietary and open-source MLLMs.
  arXiv  Detail & Related papers  (2024-01-26T18:53:03Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)
• SCALE: Synergized Collaboration of Asymmetric Language Translation Engines [105.8983433641208]
  We introduce a collaborative framework that connects compact Specialized Translation Models (STMs) and general-purpose Large Language Models (LLMs) as one unified translation engine. By introducing translation from STM into the triplet in-context demonstrations, SCALE unlocks refinement and pivoting ability of LLM. Our experiments show that SCALE significantly outperforms both few-shot LLMs (GPT-4) and specialized models (NLLB) in challenging low-resource settings.
  arXiv  Detail & Related papers  (2023-09-29T08:46:38Z)
• Impact of Large Language Models on Generating Software Specifications [14.88090169737112]
  Large Language Models (LLMs) have been successfully applied to numerous software engineering tasks. We evaluate the capabilities of LLMs for generating software specifications from software comments or documentation.
  arXiv  Detail & Related papers  (2023-06-06T00:28:39Z)
• On the Tool Manipulation Capability of Open-source Large Language Models [19.6917640220883]
  We show can we enhance open-source LLMs to be competitive to leading closed LLM APIs in tool manipulation. Our techniques can boost leading open-source LLMs by up to 90% success rate, showing capabilities competitive to OpenAI GPT-4 in 4 out of 8 ToolBench tasks.
  arXiv  Detail & Related papers  (2023-05-25T22:10:20Z)
• Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization [66.08074487429477]
  We investigate the stability and reliability of large language models (LLMs) as automatic evaluators for abstractive summarization. We find that while ChatGPT and GPT-4 outperform the commonly used automatic metrics, they are not ready as human replacements.
  arXiv  Detail & Related papers  (2023-05-22T14:58:13Z)

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.