Democratizing LLMs: An Exploration of Cost-Performance Trade-offs in Self-Refined Open-Source Models

Abstract

The dominance of proprietary LLMs has led to restricted access and raised information privacy concerns. High-performing open-source alternatives are crucial for information-sensitive and high-volume applications but often lag behind in performance. To address this gap, we propose (1) A untargeted variant of iterative self-critique and self-refinement devoid of external influence. (2) A novel ranking metric - Performance, Refinement, and Inference Cost Score (PeRFICS) - to find the optimal model for a given task considering refined performance and cost. Our experiments show that 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 on the Vicuna benchmark. Vicuna-13B takes it a step further and outperforms ChatGPT post-refinement. This work has profound implications for resource-constrained and information-sensitive environments seeking to leverage LLMs without incurring prohibitive costs, compromising on performance and privacy. The domain-agnostic self-refinement process coupled with our novel ranking metric facilitates informed decision-making in model selection, thereby reducing costs and democratizing access to high-performing language models, as evidenced by case studies.

Accepted to Findings of EMNLP 2023

References in corpus (11)

• LLaMA: Open and Efficient Foundation Language Models
• LoRA: Low-Rank Adaptation of Large Language Models
• PaLM: Scaling Language Modeling with Pathways
• Scaling Instruction-Finetuned Language Models
• Training Compute-Optimal Large Language Models
• QLoRA: Efficient Finetuning of Quantized LLMs
• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
• Reflexion: Language Agents with Verbal Reinforcement Learning
• Self-Refine: Iterative Refinement with Self-Feedback
• GPTScore: Evaluate as You Desire
• CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing