為什麼預測具規模的前沿AI模型的下游能力仍然是一個難以捉摸的問題？

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?

June 6, 2024

作者: Rylan Schaeffer, Hailey Schoelkopf, Brando Miranda, Gabriel Mukobi, Varun Madan, Adam Ibrahim, Herbie Bradley, Stella Biderman, Sanmi Koyejo

cs.AI

摘要

從擴展先進 AI 系統中預測行為的可預測性是一個非常理想的特性。儘管有許多文獻已經確立了有關預訓練性能如何擴展的知識，但有關特定下游能力如何擴展的文獻則相當混亂。在這項研究中，我們退後一步，並問：為什麼預測特定下游能力隨規模變化仍然是困難的？儘管許多因素肯定是負責的，但我們識別出一個新因素，使得在廣泛使用的多選問答基準上建模擴展行為具有挑戰性。我們使用五種模型家族和十二個確立良好的多選基準，展示了下游性能是通過負對數似然逐步降低性能與規模之間的統計關係而計算的一系列轉換。然後，我們揭示了導致這種降級的機制：下游指標需要將正確選擇與少數特定錯誤選擇進行比較，這意味著準確預測下游能力需要預測不僅是隨著規模正確選擇上的概率質量如何集中，還需要預測隨著規模錯誤選擇上的概率質量如何波動。我們實證研究了正確選擇上的概率質量如何隨著計算量的增加而與錯誤選擇上的概率質量共變，表明錯誤選擇的擴展法則可能是可以實現的。我們的工作還解釋了為什麼預訓練擴展法則通常被認為比下游能力更具可預測性，並有助於建立對前沿 AI 模型的擴展可預測性評估。

English

Predictable behavior from scaling advanced AI systems is an extremely desirable property. Although a well-established literature exists on how pretraining performance scales, the literature on how particular downstream capabilities scale is significantly muddier. In this work, we take a step back and ask: why has predicting specific downstream capabilities with scale remained elusive? While many factors are certainly responsible, we identify a new factor that makes modeling scaling behavior on widely used multiple-choice question-answering benchmarks challenging. Using five model families and twelve well-established multiple-choice benchmarks, we show that downstream performance is computed from negative log likelihoods via a sequence of transformations that progressively degrade the statistical relationship between performance and scale. We then reveal the mechanism causing this degradation: downstream metrics require comparing the correct choice against a small number of specific incorrect choices, meaning accurately predicting downstream capabilities requires predicting not just how probability mass concentrates on the correct choice with scale, but also how probability mass fluctuates on specific incorrect choices with scale. We empirically study how probability mass on the correct choice co-varies with probability mass on incorrect choices with increasing compute, suggesting that scaling laws for incorrect choices might be achievable. Our work also explains why pretraining scaling laws are commonly regarded as more predictable than downstream capabilities and contributes towards establishing scaling-predictable evaluations of frontier AI models.