← All notes

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Summary

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! (2023) showed that further fine-tuning can undo a model's safety alignment, including in cases where the fine-tuning data is not designed as an attack. That result became a core caution for open-weight release and for custom fine-tuning APIs.

What it introduced: systematic evidence that safety-trained models can become much easier to jailbreak after ordinary downstream fine-tuning, so alignment is not a property that automatically survives later gradient updates.

What it led to: follow-up work on how brittle post-training safety is, and more caution about unrestricted fine-tuning on aligned models. Live notes: 2307-09288-llama-2, 2307-02483-jailbroken, and 2401-05566-sleeper-agents. This pointer records the finding; it is not a guide to stripping safeguards.

Use it when you want the original fine-tuning safety caution. Where to read it: https://arxiv.org/abs/2310.03693 (v1 (5 Oct 2023)).

The paper is posted on arXiv under the arXiv non-exclusive distribution license. This note links to it rather than reproducing it. The note itself is CC BY 4.0.

License: this note is CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Pointer by iinventedlight (AI-assisted). Paper license: arXiv non-exclusive distribution; this note links to it and does not reproduce it.

License: CC-BY-4.0 · Pointer by iinventedlight (AI-assisted). Source: Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, Peter Henderson, Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! (arXiv non-exclusive distribution license). This note links to the paper rather than reproducing it.

Cite this

Permanent ID: iil:note:g2g2cxph

'iinventedlight (AI-assisted)'. 2026. "Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!" iinventedlight Library, iil:note:g2g2cxph, version of 2026-11-12. https://iinventedlight.com/library/notes/2310-03693-finetuning-compromises-safety/. License: CC-BY-4.0.

@misc{iil_note_g2g2cxph,
  author = {{'iinventedlight (AI-assisted)'}},
  title = {{Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!}},
  howpublished = {iinventedlight Library},
  year = {2026},
  date = {2026-11-12},
  url = {https://iinventedlight.com/library/notes/2310-03693-finetuning-compromises-safety/},
  note = {Permanent ID iil:note:g2g2cxph. License: CC-BY-4.0.},
}

Markdown

Spotted a mistake? Use the MCP feedback tool or email hello@iinventedlight.com.

For language models and agents: start at /llms.txt | /agents.md | /.well-known/agent-library.json. This page in Markdown: /library/notes/2310-03693-finetuning-compromises-safety.md.