Table of Links Abstract and Introduction
Related Work
Experiments

3.1 Design
3.2 Results
3.3 Comparison 2: Instruction-tuned vs. Dolly-tuned variants
3.4 Comparison 3: Instruction-tuned vs. community-tuned variants


Discussion
Limitations and Future Work
Conclusion, Acknowledgments and Disclosure of Funding, and References Abstract and Introduction Abstract and Introduction Related Work Related Work Experiments

3.1 Design
3.2 Results
3.3 Comparison 2: Instruction-tuned vs. Dolly-tuned variants
3.4 Comparison 3: Instruction-tuned vs. community-tuned variants 3.1 Design
3.2 Results
3.3 Comparison 2: Instruction-tuned vs. Dolly-tuned variants
3.4 Comparison 3: Instruction-tuned vs. community-tuned variants 3.1 Design 3.1 Design 3.2 Results 3.2 Results 3.3 Comparison 2: Instruction-tuned vs. Dolly-tuned variants 3.3 Comparison 2: Instruction-tuned vs. Dolly-tuned variants 3.4 Comparison 3: Instruction-tuned vs. community-tuned variants 3.4 Comparison 3: Instruction-tuned vs. community-tuned variants Discussion Discussion Limitations and Future Work Limitations and Future Work Conclusion, Acknowledgments and Disclosure of Funding, and References Conclusion, Acknowledgments and Disclosure of Funding, and References A. Models assessed A. Models assessed B. Data & Code B. Data & Code NeurIPS Paper Checklist NeurIPS Paper Checklist 6 Conclusion Fine-tuning models via repositories such as the Hugging Face Model Hub has become increasingly popular thanks to increasingly capable open models. This work has shown how fine-tuning can impact toxicity rates in hard-to-predict ways, across models from different AI labs. Model creators’ efforts to reduce toxicity during the instruction-tuning process can easily and inadvertently be undone when models are further fine-tuned on non-adversarial datasets. This phenomenon can be seen in practice in popular models fine-tuned by community contributors, where models fine-tuned for issues like multilingual capabilities can see surprisingly variable toxicity rates. These results emphasize the need for model creators, community contributors, model users, and policy-makers to pay attention to the toxicity performance of fine-tuned models, even when fine-tuning does not target toxicity. Acknowledgments and Disclosure of Funding The authors would like to thank the following individuals for helpful discussions and feedback throughout the course of this project: Kevin McKee, Inga Campos, Seliem El-Sayed, Laura Weidinger, Ramona Comanescu, and Charvi Rastogi. Brent Mittelstadt and Chris Russell’s contributions to this work have been supported through research funding provided by the Wellcome Trust (grant nr 223765/Z/21/Z), Sloan Foundation (grant nr G2021-16779), Department of Health and Social Care, EPSRC (grant nr EP/Y019393/1), and Luminate Group. Their funding supports the Trustworthiness Auditing for AI project and Governance of Emerging Technologies research programme at the Oxford Internet Institute, University of Oxford. During the course of this work Will Hawkins held an employed position at Google DeepMind. References Anthropic. (2023). Claude 2. https://www.anthropic.com/news/claude-2 Biderman, D., Portes, J., Ortiz, J. J. G., Paul, M., Greengard, P., Jennings, C., King, D., Havens, S., Chiley, V., Frankle, J., Blakeney, C., & Cunningham, J. P. (2024). LoRA Learns Less and Forgets Less (arXiv:2405.09673). arXiv. http://arxiv.org/abs/2405.09673 Bilenko, M. (2024, April 23). Introducing Phi-3: Redefining what’s possible with SLMs. Microsoft Azure Blog. https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/ Cecchini, D., Nazir, A., Chakravarthy, K., & Kocaman, V. (2024). Holistic Evaluation of Large Language Models: Assessing Robustness, Accuracy, and Toxicity for Real-World Applications. In A. Ovalle, K.-W. Chang, Y. T. Cao, N. Mehrabi, J. Zhao, A. Galstyan, J. Dhamala, A. Kumar, & R. Gupta (Eds.), Proceedings of the 4th Workshop on Trustworthy Natural Language Processing (TrustNLP 2024) (pp. 109–117). Association for Computational Linguistics. https://doi.org/10.18653/v1/2024.trustnlp-1.11 Conover, M., Hayes, M., Mathur, A., Xie, J., Wan, J., Shah, S., Ghodsi, A., Wendell, P., Zaharia, M., & Xin, R. (2023, December 4). Free Dolly: Introducing the World’s First Truly Open Instruction-Tuned LLM. Databricks. https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm Davidson, T., Warmsley, D., Macy, M., & Weber, I. (2017). Automated Hate Speech Detection and the Problem of Offensive Language (arXiv:1703.04009). arXiv. http://arxiv.org/abs/1703.04009 Dawson, N. V., & Weiss, R. (2012). Dichotomizing Continuous Variables in Statistical Analysis: A Practice to Avoid. Medical Decision Making, 32(2), 225–226. https://doi.org/10.1177/0272989X12437605 Fu, Z., Yang, H., So, A. M.-C., Lam, W., Bing, L., & Collier, N. (2022). On the Effectiveness of ParameterEfficient Fine-Tuning (arXiv:2211.15583). arXiv. https://doi.org/10.48550/arXiv.2211.15583 Gehman, S., Gururangan, S., Sap, M., Choi, Y., & Smith, N. A. (2020). RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models (arXiv:2009.11462). arXiv. http://arxiv.org/abs/2009.11462 Gelman, A. (2006). Prior distributions for variance parameters in hierarchical models (comment on article by Browne and Draper). Bayesian Analysis, 1(3), 515–534. https://doi.org/10.1214/06-BA117A Gemini Team, Anil, R., Borgeaud, S., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., Millican, K., Silver, D., Johnson, M., Antonoglou, I., Schrittwieser, J., Glaese, A., Chen, J., Pitler, E., Lillicrap, T., Lazaridou, A., . . . Vinyals, O. (2024). Gemini: A Family of Highly Capable Multimodal Models (arXiv:2312.11805). arXiv. https://doi.org/10.48550/arXiv.2312.11805 Gemma Team, Mesnard, T., Hardin, C., Dadashi, R., Bhupatiraju, S., Pathak, S., Sifre, L., Rivière, M., Kale, M. S., Love, J., Tafti, P., Hussenot, L., Sessa, P. G., Chowdhery, A., Roberts, A., Barua, A., Botev, A., Castro-Ros, A., Slone, A., . . . Kenealy, K. (2024). Gemma: Open Models Based on Gemini Research and Technology (arXiv:2403.08295). arXiv. http://arxiv.org/abs/2403.08295 He, L., Xia, M., & Henderson, P. (2024). What’s in Your ‘Safe’ Data?: Identifying Benign Data that Breaks Safety (arXiv:2404.01099). arXiv. http://arxiv.org/abs/2404.01099 Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021). LoRA: Low-Rank Adaptation of Large Language Models (arXiv:2106.09685). arXiv. https://doi.org/10.48550/arXiv.2106.09685 HuggingFace. (2024, May 18). The Model Hub. https://huggingface.co/docs/hub/en/models-the-hub Irwin, J. R., & McClelland, G. H. (2003). Negative Consequences of Dichotomizing Continuous Predictor Variables. Journal of Marketing Research, 40(3), 366–371. https://doi.org/10.1509/jmkr.40.3.366.19237 Kumar, D., Kumar, A., Agarwal, S., & Harshangi, P. (2024). Increased LLM Vulnerabilities from Fine-tuning and Quantization (arXiv:2404.04392). arXiv. http://arxiv.org/abs/2404.04392 Lermen, S., Rogers-Smith, C., & Ladish, J. (2023). LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B (arXiv:2310.20624). arXiv. https://doi.org/10.48550/arXiv.2310.20624 Liu, H., Liu, Z., Tang, R., Yuan, J., Zhong, S., Chuang, Y.-N., Li, L., Chen, R., & Hu, X. (2024). LoRA-as-an-Attack! Piercing LLM Safety Under The Share-and-Play Scenario (arXiv:2403.00108). arXiv. http://arxiv.org/abs/2403.00108 Luo, Y., Yang, Z., Meng, F., Li, Y., Zhou, J., & Zhang, Y. (2024). An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning (arXiv:2308.08747). arXiv. http://arxiv.org/abs/2308.08747 Meta. (2024a). Introducing Meta Llama 3: The most capable openly available LLM to date. Meta AI. https://ai.meta.com/blog/meta-llama-3/ Meta. (2024b). Our responsible approach to Meta AI and Meta Llama 3. Meta AI. https://ai.meta.com/blog/metallama-3-meta-ai-responsibility/ Nadeau, D., Kroutikov, M., McNeil, K., & Baribeau, S. (2024). Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations (arXiv:2404.09785). arXiv. http://arxiv.org/abs/2404.09785 OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., Avila, R., Babuschkin, I., Balaji, S., Balcom, V., Baltescu, P., Bao, H., Bavarian, M., Belgum, J., . . . Zoph, B. (2024). GPT-4 Technical Report (arXiv:2303.08774). arXiv. https://doi.org/10.48550/arXiv.2303.08774 Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., & Lowe, R. (2022). Training language models to follow instructions with human feedback (arXiv:2203.02155). arXiv. https://doi.org/10.48550/arXiv.2203.02155 Phi-3 Safety Post-Training: Aligning Language Models with a “Break-Fix” Cycle. (2024). Retrieved 27 September 2024, from https://arxiv.org/html/2407.13833v1 Qi, X., Zeng, Y., Xie, T., Chen, P.-Y., Jia, R., Mittal, P., & Henderson, P. (2023). Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! (arXiv:2310.03693). arXiv. http://arxiv.org/abs/2310.03693 Royston, P., Altman, D. G., & Sauerbrei, W. (2006). Dichotomizing continuous predictors in multiple regression: A bad idea. Statistics in Medicine, 25(1), 127–141. https://doi.org/10.1002/sim.2331 Sun, A. Y., Zemour, E., Saxena, A., Vaidyanathan, U., Lin, E., Lau, C., & Mugunthan, V. (2024). Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information? (arXiv:2307.16382). arXiv. http://arxiv.org/abs/2307.16382 Taraghi, M., Dorcelus, G., Foundjem, A., Tambon, F., & Khomh, F. (2024). Deep Learning Model Reuse in the HuggingFace Community: Challenges, Benefit and Trends (arXiv:2401.13177). arXiv. http://arxiv.org/abs/2401.13177 Tian, K., Mitchell, E., Yao, H., Manning, C. D., & Finn, C. (2023). Fine-tuning Language Models for Factuality (arXiv:2311.08401). arXiv. http://arxiv.org/abs/2311.08401 Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., Bikel, D., Blecher, L., Ferrer, C. C., Chen, M., Cucurull, G., Esiobu, D., Fernandes, J., Fu, J., Fu, W., . . . Scialom, T. (2023). Llama 2: Open Foundation and Fine-Tuned Chat Models (arXiv:2307.09288). arXiv. http://arxiv.org/abs/2307.09288 Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention Is All You Need (arXiv:1706.03762). arXiv. http://arxiv.org/abs/1706.03762 Vidgen, B., Thrush, T., Waseem, Z., & Kiela, D. (2020, December 31). Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection. arXiv.Org. https://arxiv.org/abs/2012.15761v2 Wan, A., Wallace, E., Shen, S., & Klein, D. (2023). Poisoning Language Models During Instruction Tuning. Proceedings of the 40th International Conference on Machine Learning, 35413–35425. https://proceedings.mlr.press/v202/wan23b.html Wang, S., Wang, P., Zhou, T., Dong, Y., Tan, Z., & Li, J. (2024). CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models (arXiv:2407.02408). arXiv. https://doi.org/10.48550/arXiv.2407.02408 Wang, Y., Ivison, H., Dasigi, P., Hessel, J., Khot, T., Chandu, K. R., Wadden, D., MacMillan, K., Smith, N. A., Beltagy, I., & Hajishirzi, H. (2023). How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources (arXiv:2306.04751). arXiv. https://doi.org/10.48550/arXiv.2306.04751 Weidinger, L., Mellor, J., Rauh, M., Griffin, C., Uesato, J., Huang, P.-S., Cheng, M., Glaese, M., Balle, B., Kasirzadeh, A., Kenton, Z., Brown, S., Hawkins, W., Stepleton, T., Biles, C., Birhane, A., Haas, J., Rimell, L., Hendricks, L. A., . . . Gabriel, I. (2021). Ethical and social risks of harm from Language Models (arXiv:2112.04359). arXiv. http://arxiv.org/abs/2112.04359 Yang, X., Wang, X., Zhang, Q., Petzold, L., Wang, W. Y., Zhao, X., & Lin, D. (2023). Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models (arXiv:2310.02949). arXiv. https://doi.org/10.48550/arXiv.2310.02949 Zeng, Y., & Lee, K. (2024). The Expressive Power of Low-Rank Adaptation (arXiv:2310.17513). arXiv. http://arxiv.org/abs/2310.17513 Zhan, Q., Fang, R., Bindu, R., Gupta, A., Hashimoto, T., & Kang, D. (2024). Removing RLHF Protections in GPT-4 via Fine-Tuning (arXiv:2311.05553). arXiv. http://arxiv.org/abs/2311.05553 Zhang, S., Dong, L., Li, X., Zhang, S., Sun, X., Wang, S., Li, J., Hu, R., Zhang, T., Wu, F., & Wang, G. (2024). Instruction Tuning for Large Language Models: A Survey (arXiv:2308.10792). arXiv. http://arxiv.org/abs/2308.10792 Zhao, J., Deng, Z., Madras, D., Zou, J., & Ren, M. (2024). Learning and Forgetting Unsafe Examples in Large Language Models (arXiv:2312.12736). arXiv. http://arxiv.org/abs/2312.12736 Authors:
(1) Will Hawkins, Oxford Internet Institute University of Oxford;
(2) Brent Mittelstadt, Oxford Internet Institute University of Oxford;
(3) Chris Russell, Oxford Internet Institute University of Oxford. Authors: Authors: (1) Will Hawkins, Oxford Internet Institute University of Oxford; (2) Brent Mittelstadt, Oxford Internet Institute University of Oxford; (3) Chris Russell, Oxford Internet Institute University of Oxford. This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

Quant

Databricks

Dolly

Empirical

Microsoft

Open Models, Closed Gaps: How Fine-Tuning Impacts AI Model Toxicity

Fine-Tuning Can Accidentally Make AI More Toxic, Study Finds

Model Tuning Technology

Too Long; Didn't Read

Why AI Models Get More Toxic After Community Fine-Tuning

Why AI Models Get More Toxic After Community Fine-Tuning

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Ablative Study on Domain Adapter, Motion Module Design, and MotionLoRA Efficiency

How Fine-Tuning Open AI Models Can Reintroduce Toxicity

The Dark Side of AI Fine-Tuning

Community-Tuned AI Models Are Popular—But Are They Safe?

Can AI Be Taught to Be Less Toxic? New Findings Say Yes (But...)

Multilingual AI Fine-Tuning Shows Mixed Results on Toxicity

Ablative Study on Domain Adapter, Motion Module Design, and MotionLoRA Efficiency

How Fine-Tuning Open AI Models Can Reintroduce Toxicity

The Dark Side of AI Fine-Tuning

Community-Tuned AI Models Are Popular—But Are They Safe?

Can AI Be Taught to Be Less Toxic? New Findings Say Yes (But...)

Multilingual AI Fine-Tuning Shows Mixed Results on Toxicity

Light-Mode

Classic

Newspaper

Minty

Dark-Mode

Neon Noir

Minty

HN StartUps