# Chained Tuning Leads to Biased Forgetting

arXiv: https://arxiv.org/abs/2412.16469 · HTML: https://mlsanity.com/paper/2412.16469/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 43 references that are in the map.
- First posted on arXiv 21 Dec 2024.

## Builds on (most cited first, 30 of 31)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Three Factors Influencing Minima in SGD](https://mlsanity.com/paper/1711.04623/) (2017)
- [Progressive Prompts: Continual Learning for Language Models](https://mlsanity.com/paper/2301.12314/) (2023)
- [Episodic Memory in Lifelong Language Learning](https://mlsanity.com/paper/1906.01076/) (2019)
- [Understanding the Role of Training Regimes in Continual Learning](https://mlsanity.com/paper/2006.06958/) (2020)
- [Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics](https://mlsanity.com/paper/2007.07400/) (2020)
- [Fine-tuned Language Models are Continual Learners](https://mlsanity.com/paper/2205.12393/) (2022)
- [Linear Mode Connectivity in Multitask and Continual Learning](https://mlsanity.com/paper/2010.04495/) (2020)
- [Understanding Catastrophic Forgetting in Language Models via Implicit Inference](https://mlsanity.com/paper/2309.10105/) (2023)
- [CommonsenseQA 2.0: Exposing the Limits of AI through Gamification](https://mlsanity.com/paper/2201.05320/) (2022)
- [Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates](https://mlsanity.com/paper/2402.18540/) (2024)
- [SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures](https://mlsanity.com/paper/2110.07518/) (2021)

## Built on by (most cited first, 3 of 3)

- [Review of Hallucination Understanding in Large Language and Vision Models](https://mlsanity.com/paper/2510.00034/) (2025)
- [Fine-tuning MLLMs Without Forgetting Is Easier Than You Think](https://mlsanity.com/paper/2603.14493/) (2026)
- [Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model](https://mlsanity.com/paper/2609.11291/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are often fine-tuned for use on downstream tasks, though this can degrade capabilities learned during previous training. This phenomenon, often referred to as catastrophic forgetting, has important potential implications for the safety of deployed models. In this work, we first show that models trained on downstream tasks forget their safety tuning to a greater extent than models trained in the opposite order. Second, we show that forgetting disproportionately impacts safety information about certain groups. To quantify this phenomenon, we define a new metric we term biased forgetting. We conduct a systematic evaluation of the effects of task ordering on forgetting and apply mitigations that can help the model recover from the forgetting observed. We hope our findings can better inform methods for chaining the finetuning of LLMs in continual learning settings to enable training of safer and less toxic models.