# RobustFT: Robust Supervised Fine-tuning for Large Language Models under Noisy Response

arXiv: https://arxiv.org/abs/2412.14922 · HTML: https://mlsanity.com/paper/2412.14922/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2024.

## Built on by (most cited first, 24 of 24)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems](https://mlsanity.com/paper/2506.13666/) (2025)
- [Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation](https://mlsanity.com/paper/2501.18100/) (2025)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning](https://mlsanity.com/paper/2505.16559/) (2025)
- [Gradient Surgery for Safe LLM Fine-Tuning](https://mlsanity.com/paper/2508.07172/) (2025)
- [A Survey on Efficient Large Language Model Training: From Data-centric Perspectives](https://mlsanity.com/paper/2510.25817/) (2025)
- [Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization](https://mlsanity.com/paper/2601.04992/) (2026)
- [Scalable Valuation of Human Feedback through Provably Robust Model Alignment](https://mlsanity.com/paper/2505.17859/) (2025)
- [Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning](https://mlsanity.com/paper/2508.04329/) (2025)
- [Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink](https://mlsanity.com/paper/2602.05228/) (2026)
- [GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback](https://mlsanity.com/paper/2604.08553/) (2026)
- [Fine-Tuning on Noisy Instructions: Effects on Generalization and Performance](https://mlsanity.com/paper/2510.03528/) (2025)
- [ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction](https://mlsanity.com/paper/2503.20978/) (2025)
- [REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations](https://mlsanity.com/paper/2604.17289/) (2026)
- [Weed Out, Then Harvest: Dual Low-Rank Adaptation is an Effective Noisy Label Detector for Noise-Robust Learning](https://mlsanity.com/paper/2510.10208/) (2025)
- [MANTRA: a Framework for Multi-stage Adaptive Noise TReAtment During Training](https://mlsanity.com/paper/2512.04319/) (2025)
- [Self Distillation Fine-Tuning of Protein Language Models Improves Versatility in Protein Design](https://mlsanity.com/paper/2512.09329/) (2025)
- [KALE: Enhancing Knowledge Manipulation in Large Language Models via Knowledge-aware Learning](https://mlsanity.com/paper/2601.07430/) (2026)
- [Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority](https://mlsanity.com/paper/2602.01227/) (2026)
- [Analyzing the Effect of Noise in LLM Fine-tuning](https://mlsanity.com/paper/2604.12469/) (2026)
- [Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching](https://mlsanity.com/paper/2606.11583/) (2026)
- [Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation](https://mlsanity.com/paper/2608.05341/) (2026)
- [Every Batch Is Its Own Validation Set: Leave-One-Out Gradient Matching for Online Data Selection in LLM Fine-Tuning](https://mlsanity.com/paper/2610.00436/) (2026)

## Abstract (arXiv)

Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the collected data inevitably contains noise in practical applications, which poses significant challenges to model performance on downstream tasks. Therefore, there is an urgent need for a noise-robust SFT framework to enhance model capabilities in downstream tasks. To address this challenge, we introduce a robust SFT framework (RobustFT) that performs noise detection and relabeling on downstream task data. For noise identification, our approach employs a multi-expert collaborative system with inference-enhanced models to achieve superior noise detection. In the denoising phase, we utilize a context-enhanced strategy, which incorporates the most relevant and confident knowledge followed by careful assessment to generate reliable annotations. Additionally, we introduce an effective data selection mechanism based on response entropy, ensuring only high-quality samples are retained for fine-tuning. Extensive experiments conducted on multiple LLMs across five datasets demonstrate RobustFT's exceptional performance in noisy scenarios.