# Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning

arXiv: https://arxiv.org/abs/2402.13669 · HTML: https://mlsanity.com/paper/2402.13669/

## Key facts

- Cited by 96 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 36 of its 50 references that are in the map.
- First posted on arXiv 21 Feb 2024.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 30 of 36)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [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)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models](https://mlsanity.com/paper/2401.01335/) (2024)

## Built on by (most cited first, 30 of 96)

- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [Reinforcement Learning via Self-Distillation](https://mlsanity.com/paper/2601.20802/) (2026)
- [Self-Distillation Enables Continual Learning](https://mlsanity.com/paper/2601.19897/) (2026)
- [CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation](https://mlsanity.com/paper/2502.21074/) (2025)
- [Learning Dynamics of LLM Finetuning](https://mlsanity.com/paper/2407.10490/) (2024)
- [A Survey on Self-Evolution of Large Language Models](https://mlsanity.com/paper/2404.14387/) (2024)
- [The Best Instruction-Tuning Data are Those That Fit](https://mlsanity.com/paper/2502.04194/) (2025)
- [DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment](https://mlsanity.com/paper/2507.02768/) (2025)
- [The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It](https://mlsanity.com/paper/2505.24119/) (2025)
- [Aligning Language Models from User Interactions](https://mlsanity.com/paper/2603.12273/) (2026)
- [LLAVADI: What Matters For Multimodal Large Language Models Distillation](https://mlsanity.com/paper/2407.19409/) (2024)
- [Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking](https://mlsanity.com/paper/2505.20023/) (2025)
- [L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models](https://mlsanity.com/paper/2505.17505/) (2025)
- [Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning](https://mlsanity.com/paper/2501.14315/) (2025)
- [E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning](https://mlsanity.com/paper/2409.06679/) (2024)
- [Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling](https://mlsanity.com/paper/2411.00750/) (2024)
- [FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction](https://mlsanity.com/paper/2509.18362/) (2025)
- [APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training](https://mlsanity.com/paper/2506.03483/) (2025)
- [TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use](https://mlsanity.com/paper/2412.15495/) (2024)
- [Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging](https://mlsanity.com/paper/2412.19512/) (2024)
- [Escaping Collapse: The Strength of Weak Data for Large Language Model Training](https://mlsanity.com/paper/2502.08924/) (2025)
- [Krutrim LLM: Multilingual Foundational Model for over a Billion People](https://mlsanity.com/paper/2502.09642/) (2025)
- [Multi-Rollout On-Policy Distillation via Peer Successes and Failures](https://mlsanity.com/paper/2605.12652/) (2026)
- [Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs](https://mlsanity.com/paper/2506.10508/) (2025)
- [SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment](https://mlsanity.com/paper/2509.03934/) (2025)
- [TAIA: Large Language Models are Out-of-Distribution Data Learners](https://mlsanity.com/paper/2405.20192/) (2024)
- [Unified Active Retrieval for Retrieval Augmented Generation](https://mlsanity.com/paper/2406.12534/) (2024)
- [Self-Data Distillation for Recovering Quality in Pruned Large Language Models](https://mlsanity.com/paper/2410.09982/) (2024)
- [OntoTune: Ontology-Driven Self-training for Aligning Large Language Models](https://mlsanity.com/paper/2502.05478/) (2025)
- [DIFFA: Large Language Diffusion Models Can Listen and Understand](https://mlsanity.com/paper/2507.18452/) (2025)

## Abstract (arXiv)

The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instruction-following abilities. In this paper, we posit that the distribution gap between task datasets and the LLMs serves as the primary underlying cause. To address the problem, we introduce Self-Distillation Fine-Tuning (SDFT), a novel approach that bridges the distribution gap by guiding fine-tuning with a distilled dataset generated by the model itself to match its original distribution. Experimental results on the Llama-2-chat model across various benchmarks demonstrate that SDFT effectively mitigates catastrophic forgetting while achieving comparable or superior performance on downstream tasks compared to the vanilla fine-tuning. Moreover, SDFT demonstrates the potential to maintain the helpfulness and safety alignment of LLMs. Our code is available at https://github.com/sail-sg/sdft.