# Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models

arXiv: https://arxiv.org/abs/2312.14751 · HTML: https://mlsanity.com/paper/2312.14751/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 89 references that are in the map.
- First posted on arXiv 22 Dec 2023.

## Builds on (most cited first, 30 of 65)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Orca: Progressive Learning from Complex Explanation Traces of GPT-4](https://mlsanity.com/paper/2306.02707/) (2023)
- [Learning How to Ask: Querying LMs with Mixtures of Soft Prompts](https://mlsanity.com/paper/2104.06599/) (2021)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)
- [Fine-Tuning Language Models with Just Forward Passes](https://mlsanity.com/paper/2305.17333/) (2023)
- [ZeRO-Offload: Democratizing Billion-Scale Model Training](https://mlsanity.com/paper/2101.06840/) (2021)
- [Synthetic Data from Diffusion Models Improves ImageNet Classification](https://mlsanity.com/paper/2304.08466/) (2023)
- [The False Promise of Imitating Proprietary LLMs](https://mlsanity.com/paper/2305.15717/) (2023)
- [Self-Consuming Generative Models Go MAD](https://mlsanity.com/paper/2307.01850/) (2023)

## Built on by (most cited first, 7 of 7)

- [Representation Noising: A Defence Mechanism Against Harmful Finetuning](https://mlsanity.com/paper/2405.14577/) (2024)
- [Risks and Opportunities of Open-Source Generative AI](https://mlsanity.com/paper/2405.08597/) (2024)
- [Towards Data Governance of Frontier AI Models](https://mlsanity.com/paper/2412.03824/) (2024)
- [Forecasting Open-Weight AI Model Growth on HuggingFace](https://mlsanity.com/paper/2502.15987/) (2025)
- [Countering Autonomous Cyber Threats](https://mlsanity.com/paper/2410.18312/) (2024)
- [Generative AI for Accessible and Inclusive Extended Reality](https://mlsanity.com/paper/2410.23803/) (2024)
- [Opening the Scope of Openness in AI](https://mlsanity.com/paper/2505.06464/) (2025)

## Abstract (arXiv)

Public release of the weights of pretrained foundation models, otherwise known as downloadable access citepsolaimangradient2023, enables fine-tuning without the prohibitive expense of pretraining. Our work argues that increasingly accessible fine-tuning of downloadable models may increase hazards. First, we highlight research to improve the accessibility of fine-tuning. We split our discussion into research that A) reduces the computational cost of fine-tuning and B) improves the ability to share that cost across more actors. Second, we argue that increasingly accessible fine-tuning methods may increase hazard through facilitating malicious use and making oversight of models with potentially dangerous capabilities more difficult. Third, we discuss potential mitigatory measures, as well as benefits of more accessible fine-tuning. Given substantial remaining uncertainty about hazards, we conclude by emphasizing the urgent need for the development of mitigations.