XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML

• URL: http://arxiv.org/abs/2508.00924v1
• Date: Wed, 30 Jul 2025 10:46:16 GMT
• Title: XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML
• Authors: Ernesto L. Estevanell-Valladares, Suilan Estevez-Velarde, Yoan Gutiérrez, Andrés Montoyo, Ruslan Mitkov,
• Abstract summary: We introduce XAutoLM, a meta-learning-augmented AutoML framework for fine-tuning language models.<n>XAutoLM learns from stored successes and failures to optimise discriminative and generative LM fine-tuning pipelines efficiently.<n>On four text classification and two question-answering benchmarks, XAutoLM surpasses zero-shot optimiser's peak F1 on five of six tasks.
• Score: 4.635612366838524
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Experts in machine learning leverage domain knowledge to navigate decisions in model selection, hyperparameter optimisation, and resource allocation. This is particularly critical for fine-tuning language models (LMs), where repeated trials incur substantial computational overhead and environmental impact. However, no existing automated framework simultaneously tackles the entire model selection and HPO task for resource-efficient LM fine-tuning. We introduce XAutoLM, a meta-learning-augmented AutoML framework that reuses past experiences to optimise discriminative and generative LM fine-tuning pipelines efficiently. XAutoLM learns from stored successes and failures by extracting task- and system-level meta-features to bias its sampling toward fruitful configurations and away from costly dead ends. On four text classification and two question-answering benchmarks, XAutoLM surpasses zero-shot optimiser's peak F1 on five of six tasks, cuts mean evaluation time by up to 4.5x, reduces error ratios by up to sevenfold, and uncovers up to 50% more pipelines above the zero-shot Pareto front. In contrast, simpler memory-based baselines suffer negative transfer. We release XAutoLM and our experience store to catalyse resource-efficient, Green AI fine-tuning in the NLP community.

Related papers

• EDCA - An Evolutionary Data-Centric AutoML Framework for Efficient Pipelines [0.276240219662896]
  This work presents EDCA, an Evolutionary Data Centric AutoML framework.<n>Data quality is usually an overlooked part of AutoML and continues to be a manual and time-consuming task.<n> EDCA was compared to FLAML and TPOT, two frameworks at the top of the AutoML benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T11:46:07Z)
• LLM-AutoDiff: Auto-Differentiate Any LLM Workflow [58.56731133392544]
  We introduce LLM-AutoDiff: a novel framework for Automatic Prompt Engineering (APE)<n>LLMs-AutoDiff treats each textual input as a trainable parameter and uses a frozen backward engine to generate feedback-akin to textual gradients.<n>It consistently outperforms existing textual gradient baselines in both accuracy and training cost.
  arXiv  Detail & Related papers  (2025-01-28T03:18:48Z)
• SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learning [14.702694298483445]
  Tree-Search Enhanced LLM Agents (SELA) is an agent-based system that leverages Monte Carlo Tree Search (MCTS) to optimize the AutoML process. SELA represents pipeline configurations as trees, enabling agents to conduct experiments intelligently and iteratively refine their strategies. In an extensive evaluation across 20 machine learning datasets, we compare the performance of traditional and agent-based AutoML methods.
  arXiv  Detail & Related papers  (2024-10-22T17:56:08Z)
• Large Language Models can be Strong Self-Detoxifiers [82.6594169242814]
  Self-disciplined Autoregressive Sampling (SASA) is a lightweight controlled decoding algorithm for toxicity reduction of large language models (LLMs) SASA tracks the margin of the current output to steer the generation away from the toxic subspace, by adjusting the autoregressive sampling strategy. evaluated on LLMs of different scale and nature, namely Llama-3.1-Instruct (8B), Llama-2 (7B), and GPT2-L models with the RealToxicityPrompts, BOLD, and AttaQ benchmarks.
  arXiv  Detail & Related papers  (2024-10-04T17:45:15Z)
• AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML [56.565200973244146]
  Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline.<n>Recent works have started exploiting large language models (LLM) to lessen such burden.<n>This paper proposes AutoML-Agent, a novel multi-agent framework tailored for full-pipeline AutoML.
  arXiv  Detail & Related papers  (2024-10-03T20:01:09Z)
• Verbalized Machine Learning: Revisiting Machine Learning with Language Models [63.10391314749408]
  We introduce the framework of verbalized machine learning (VML)<n>VML constrains the parameter space to be human-interpretable natural language.<n>We empirically verify the effectiveness of VML, and hope that VML can serve as a stepping stone to stronger interpretability.
  arXiv  Detail & Related papers  (2024-06-06T17:59:56Z)
• AutoMix: Automatically Mixing Language Models [62.51238143437967]
  Large language models (LLMs) are now available from cloud API providers in various sizes and configurations.<n>We present Automix, an approach that strategically routes queries to larger LMs, based on the approximate correctness of outputs from a smaller LM.
  arXiv  Detail & Related papers  (2023-10-19T17:57:39Z)
• MLLM-DataEngine: An Iterative Refinement Approach for MLLM [62.30753425449056]
  We propose a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results. For targeting, we propose an Adaptive Bad-case Sampling module, which adjusts the ratio of different types of data. For quality, we resort to GPT-4 to generate high-quality data with each given data type.
  arXiv  Detail & Related papers  (2023-08-25T01:41:04Z)
• AutoEn: An AutoML method based on ensembles of predefined Machine Learning pipelines for supervised Traffic Forecasting [1.6242924916178283]
  Traffic Forecasting (TF) is gaining relevance due to its ability to mitigate traffic congestion by forecasting future traffic states. TF poses one big challenge to the Machine Learning paradigm, known as the Model Selection Problem (MSP) We introduce AutoEn, which is a simple and efficient method for automatically generating multi-classifier ensembles from a predefined set of ML pipelines.
  arXiv  Detail & Related papers  (2023-03-19T18:37:18Z)
• Robusta: Robust AutoML for Feature Selection via Reinforcement Learning [24.24652530951966]
  We propose the first robust AutoML framework, Robusta--based on reinforcement learning (RL) We show that the framework is able to improve the model robustness by up to 22% while maintaining competitive accuracy on benign samples.
  arXiv  Detail & Related papers  (2021-01-15T03:12:29Z)
• Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning [45.643809726832764]
  We introduce new AutoML approaches motivated by our winning submission to the second ChaLearn AutoML challenge. We develop PoSH Auto-sklearn, which enables AutoML systems to work well on large datasets under rigid time limits. We also propose a solution towards truly hands-free AutoML.
  arXiv  Detail & Related papers  (2020-07-08T12:41:03Z)

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.