# Scaling Laws Do Not Scale

arXiv: https://arxiv.org/abs/2307.03201 · HTML: https://mlsanity.com/paper/2307.03201/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 186 references that are in the map.
- First posted on arXiv 5 Jul 2023.

## Builds on (most cited first, 30 of 68)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [Multimodal datasets: misogyny, pornography, and malignant stereotypes](https://mlsanity.com/paper/2110.01963/) (2021)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [A Constructive Prediction of the Generalization Error Across Scales](https://mlsanity.com/paper/1909.12673/) (2019)
- [Are All Languages Created Equal in Multilingual BERT?](https://mlsanity.com/paper/2005.09093/) (2020)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets](https://mlsanity.com/paper/2106.10328/) (2021)
- [The Values Encoded in Machine Learning Research](https://mlsanity.com/paper/2106.15590/) (2021)

## Built on by (most cited first, 13 of 13)

- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [Paloma: A Benchmark for Evaluating Language Model Fit](https://mlsanity.com/paper/2312.10523/) (2023)
- [On the Scalability of GNNs for Molecular Graphs](https://mlsanity.com/paper/2404.11568/) (2024)
- [Position: Measure Dataset Diversity, Don't Just Claim It](https://mlsanity.com/paper/2407.08188/) (2024)
- [What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text](https://mlsanity.com/paper/2503.04804/) (2025)
- [Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor](https://mlsanity.com/paper/2506.14652/) (2025)
- [Predictable Scale: Part II, Farseer: A Refined Scaling Law in Large Language Models](https://mlsanity.com/paper/2506.10972/) (2025)
- [Position: Enough of Scaling LLMs! Lets Focus on Downscaling](https://mlsanity.com/paper/2505.00985/) (2025)
- [A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search](https://mlsanity.com/paper/2507.00004/) (2025)
- [Who Defines "Best"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards](https://mlsanity.com/paper/2604.21769/) (2026)
- [A Case for Specialisation in Non-Human Entities](https://mlsanity.com/paper/2503.04742/) (2025)
- [Linguistic properties and model scale in brain encoding: from small to compressed language models](https://mlsanity.com/paper/2602.07547/) (2026)
- [Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation](https://mlsanity.com/paper/2606.12117/) (2026)

## Abstract (arXiv)

Recent work has advocated for training AI models on ever-larger datasets, arguing that as the size of a dataset increases, the performance of a model trained on that dataset will correspondingly increase (referred to as "scaling laws"). In this paper, we draw on literature from the social sciences and machine learning to critically interrogate these claims. We argue that this scaling law relationship depends on metrics used to measure performance that may not correspond with how different groups of people perceive the quality of models' output. As the size of datasets used to train large AI models grows and AI systems impact ever larger groups of people, the number of distinct communities represented in training or evaluation datasets grows. It is thus even more likely that communities represented in datasets may have values or preferences not reflected in (or at odds with) the metrics used to evaluate model performance in scaling laws. Different communities may also have values in tension with each other, leading to difficult, potentially irreconcilable choices about metrics used for model evaluations -- threatening the validity of claims that model performance is improving at scale. We end the paper with implications for AI development: that the motivation for scraping ever-larger datasets may be based on fundamentally flawed assumptions about model performance. That is, models may not, in fact, continue to improve as the datasets get larger -- at least not for all people or communities impacted by those models. We suggest opportunities for the field to rethink norms and values in AI development, resisting claims for universality of large models, fostering more local, small-scale designs, and other ways to resist the impetus towards scale in AI.