Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
- URL: http://arxiv.org/abs/2602.14536v1
- Date: Mon, 16 Feb 2026 07:49:33 GMT
- Title: Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
- Authors: Yuchen Yang, Wenze Lin, Enhao Huang, Zhixuan Chu, Hongbin Zhou, Lan Tao, Yiming Li, Zhan Qin, Kui Ren,
- Abstract summary: XTF is an explainable token-level noise filtering framework.<n>XTF can significantly improve downstream performance by up to 13.7% compared to regular fine-tuning.
- Score: 46.275971836374026
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to specific downstream tasks, typically involves further training on corresponding datasets. However, a fundamental discrepancy exists between current fine-tuning datasets and the token-level optimization mechanism of LLMs: most datasets are designed at the sentence-level, which introduces token-level noise, causing negative influence to final performance. In this paper, we propose XTF, an explainable token-level noise filtering framework. XTF decomposes the complex and subtle contributions of token-level data to the fine-tuning process into three distinct and explicit attributes (reasoning importance, knowledge novelty, and task relevance), which can be assessed using scoring methods, and then masks the gradients of selected noisy tokens accordingly to optimize the performance of fine-tuned LLMs. We conduct extensive experiments on three representative downstream tasks (math, code and medicine) across 7 mainstream LLMs. The results demonstrate that XTF can significantly improve downstream performance by up to 13.7% compared to regular fine-tuning. Our work highlights the importance of token-level dataset optimization, and demonstrates the potential of strategies based on attribute decomposition for explaining complex training mechanisms.
Related papers
- Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches [0.0]
We explore strategies to fine-tune decoder-only Large Language Models (LLMs) for downstream text classification under resource constraints.<n>Two approaches are investigated: (1) attaching a classification head to a pre-trained causal LLM and fine-tuning on the task, and (2) instruction-tuning the LLM in a prompt->response format for classification.
arXiv Detail & Related papers (2025-12-14T13:02:06Z) - Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM [51.21051698747157]
We propose a self-adaptive gradient-aware data selection approach (GrADS) for supervised fine-tuning of large language models (LLMs)<n>Specifically, we design self-guided criteria that leverage the magnitude and statistical distribution of gradients to prioritize examples that contribute the most to the model's learning process.<n>Through extensive experimentation with various LLMs across diverse domains such as medicine, law, and finance, GrADS has demonstrated significant efficiency and cost-effectiveness.
arXiv Detail & Related papers (2025-11-07T08:34:50Z) - SLearnLLM: A Self-Learning Framework for Efficient Domain-Specific Adaptation of Large Language Models [7.44035983292392]
We propose a self-learning framework for large language models (LLMs) inspired by human learning pattern.<n>This framework takes a fine-tuning (SFT) dataset in a specific domain as input.<n>We show that our method substantially reduces training time while achieving comparable improvements to those attained with full dataset fine-tuning.
arXiv Detail & Related papers (2025-05-23T04:50:54Z) - END: Early Noise Dropping for Efficient and Effective Context Denoising [60.24648712022382]
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks.<n>They are often distracted by irrelevant or noisy context in input sequences that degrades output quality.<n>We introduce Early Noise Dropping (textscEND), a novel approach to mitigate this issue without requiring fine-tuning the LLMs.
arXiv Detail & Related papers (2025-02-26T08:07:17Z) - Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [65.23593936798662]
We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
arXiv Detail & Related papers (2025-01-24T08:18:56Z) - 60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering [50.12622877002846]
Large language models (LLMs) encode extensive world knowledge through pre-training on massive datasets, which can be fine-tuned for the question-answering (QA) task.<n>We categorize supervised fine-tuning (SFT) data based on the extent of knowledge memorized by the pretrained LLMs.<n>Our experiments show that as few as 60 data points during the SFT stage can activate the knowledge encoded during pre-training, enabling LLMs to perform the QA task.
arXiv Detail & Related papers (2024-09-24T07:38:38Z) - DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity.
Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data.
Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
arXiv Detail & Related papers (2024-06-25T04:27:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.