PandaLM：面向大语言模型指令调优优化的自动评估基准
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
AI总结：
PandaLM是一个自动评估基准，通过训练裁判大语言模型来区分更优模型，兼顾客观正确性与主观因素，实现公平低成本的LLM指令调优优化。
摘要：
对大型语言模型（LLM）进行指令调优仍是一项具有挑战性的任务，这归因于超参数选择的复杂性以及评估调优后模型的难度。为了确定最优超参数，一个自动、稳健且可靠的评估基准至关重要。然而，由于评估准确性和隐私保护方面的挑战，建立这样一个基准并非易事。针对这些挑战，我们引入了一个名为PandaLM的裁判大语言模型，该模型经过训练，能够在多个LLM中区分出更优的模型。PandaLM的关注点不仅限于响应的客观正确性——这是传统评估数据集的主要关注点——它还处理重要的主观因素，如相对简洁性、清晰度、对指令的遵循程度、全面性和正式性。为确保PandaLM的可靠性，我们收集了一个多样化的、由人工标注的测试数据集，其中所有上下文均由人类生成，标签与人类偏好一致。我们的结果表明，在我们的测试数据集上，PandaLM-7B在F1分数上达到了GPT-3.5评估能力的93.75%和GPT-4的88.28%。PandaLM使得LLM的评估更加公平且成本更低，这体现在通过PandaLM调优的模型相较于使用默认Alpaca超参数训练的对应模型所取得的显著改进上。此外，PandaLM不依赖于基于API的评估，从而避免了潜在的数据泄露。PandaLM的所有资源已在https://github.com/WeOpenML/PandaLM发布。
英文摘要：
Instruction tuning large language models (LLMs) remains a challenging task, owing to the complexity of hyperparameter selection and the difficulty involved in evaluating the tuned models. To determine the optimal hyperparameters, an automatic, robust, and reliable evaluation benchmark is essential. However, establishing such a benchmark is not a trivial task due to the challenges associated with evaluation accuracy and privacy protection. In response to these challenges, we introduce a judge large language model, named PandaLM, which is trained to distinguish the superior model given several LLMs. PandaLM's focus extends beyond just the objective correctness of responses, which is the main focus of traditional evaluation datasets. It addresses vital subjective factors such as relative conciseness, clarity, adherence to instructions, comprehensiveness, and formality. To ensure the reliability of PandaLM, we collect a diverse human-annotated test dataset, where all contexts are generated by humans and labels are aligned with human preferences. Our results indicate that PandaLM-7B achieves 93.75% of GPT-3.5's evaluation ability and 88.28% of GPT-4's in terms of F1-score on our test dataset. PandaLM enables the evaluation of LLM to be fairer but with less cost, evidenced by significant improvements achieved by models tuned through PandaLM compared to their counterparts trained with default Alpaca's hyperparameters. In addition, PandaLM does not depend on API-based evaluations, thus avoiding potential data leakage. All resources of PandaLM are released at https://github.com/WeOpenML/PandaLM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
