TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation

• URL: http://arxiv.org/abs/2506.23979v1
• Date: Mon, 30 Jun 2025 15:45:28 GMT
• Title: TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation
• Authors: Renren Jin, Tianhao Shen, Xinwei Wu, Dan Shi, Haoran Sun, Wuwei Huang, Quandong Wang, Wei Liu, Jian Luan, Bin Wang, Deyi Xiong,
• Abstract summary: Conducting supervised fine-tuning and preference fine-tuning on large language models (LLMs) requires high-quality datasets.<n>Most available datasets for supervised and preference fine-tuning are in English.<n>We propose the underlinetextbfTaxonomy-Guided underlinetextbfPreference Data Generation framework.
• Score: 50.319535974012
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conducting supervised fine-tuning and preference fine-tuning on large language models (LLMs) requires high-quality datasets to improve their ability to follow instructions and align with human preferences and values. However, constructing such datasets is resource-intensive, and most available datasets for supervised and preference fine-tuning are in English. To address these challenges, we propose the \underline{\textbf{Ta}}xonomy-Guided \underline{\textbf{P}}reference Data Generation (TaP) framework, which facilitates automated and scalable construction of preference datasets across various languages. TaP is grounded in a structured taxonomy that allows fine-grained control over dataset composition, thereby ensuring both diversity and comprehensive coverage. We employ TaP-generated datasets to perform supervised and preference fine-tuning on various LLMs. Experimental results demonstrate that LLMs trained on TaP-generated datasets outperform those trained on existing open-source datasets. Remarkably, LLMs trained on TaP-generated datasets surpass the performance of those trained on an open-source dataset that is 180 times larger.

Related papers

• Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakh [29.813758537374795]
  We introduce and open-source a large-scale (10,600 samples) instruction-following dataset, covering key institutional and cultural knowledge relevant to Kazakhstan.<n>We employ LLM-assisted data generation, comparing open-weight and closed-weight models for dataset construction, and select GPT-4o as the backbone.<n>We show that fine-tuning Qwen, Falcon, and Gemma on our dataset leads to consistent performance improvements in both multiple-choice and generative tasks.
  arXiv  Detail & Related papers  (2025-02-19T11:44:27Z)
• Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers [0.0]
  This paper presents a machine learning framework that automates dataset mention detection across research domains.<n>We employ zero-shot extraction from research papers, an LLM-as-a-Judge for quality assessment, and a reasoning agent for refinement to generate a weakly supervised synthetic dataset.<n>At inference, a ModernBERT-based classifier efficiently filters dataset mentions, reducing computational overhead while maintaining high recall.
  arXiv  Detail & Related papers  (2025-02-14T16:16:02Z)
• Generating Realistic Tabular Data with Large Language Models [49.03536886067729]
  Large language models (LLM) have been used for diverse tasks, but do not capture the correct correlation between the features and the target variable. We propose a LLM-based method with three important improvements to correctly capture the ground-truth feature-class correlation in the real data. Our experiments show that our method significantly outperforms 10 SOTA baselines on 20 datasets in downstream tasks.
  arXiv  Detail & Related papers  (2024-10-29T04:14:32Z)
• Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification [17.03832781104098]
  Citation intention Classification (CIC) tools classify citations by their intention. Prior research has shown that pretrained language models (PLMs) can achieve state-of-the-art performance on CIC benchmarks. We propose a multi-task learning framework that jointly fine-tunes PLMs on a dataset of primary interest together with multiple auxiliary CIC datasets.
  arXiv  Detail & Related papers  (2024-10-17T08:45:02Z)
• Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models [79.65071553905021]
  We propose Data Advisor, a method for generating data that takes into account the characteristics of the desired dataset. Data Advisor monitors the status of the generated data, identifies weaknesses in the current dataset, and advises the next iteration of data generation.
  arXiv  Detail & Related papers  (2024-10-07T17:59:58Z)
• Improving Multilingual Instruction Finetuning via Linguistically Natural and Diverse Datasets [38.867815476721894]
  Most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages. Traditional methods for creating multilingual IFT datasets struggle to capture linguistic nuances and ensure prompt (instruction) diversity. We propose a novel method for collecting multilingual IFT datasets that preserves linguistic naturalness and ensures prompt diversity.
  arXiv  Detail & Related papers  (2024-07-01T23:47:09Z)
• SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning [16.307467144690683]
  Large Language Models can achieve desirable performance with only a small amount of high-quality data. Identifying high-quality data from vast datasets to curate small yet effective datasets has emerged as a critical challenge. We introduce SHED, an automated dataset refinement framework based on Shapley value for instruction fine-tuning.
  arXiv  Detail & Related papers  (2024-04-23T04:56:48Z)
• Better Synthetic Data by Retrieving and Transforming Existing Datasets [63.875064274379824]
  We introduce DataTune, a method to make better use of publicly available datasets to improve automatic dataset generation. On a diverse set of language-based tasks, we find that finetuning language models via DataTune improves over a few-shot prompting baseline by 49%. We find that dataset transformation significantly increases the diversity and difficulty of generated data on many tasks.
  arXiv  Detail & Related papers  (2024-04-22T17:15:32Z)
• LESS: Selecting Influential Data for Targeted Instruction Tuning [64.78894228923619]
  We propose LESS, an efficient algorithm to estimate data influences and perform Low-rank gradiEnt Similarity Search for instruction data selection. We show that training on a LESS-selected 5% of the data can often outperform training on the full dataset across diverse downstream tasks. Our method goes beyond surface form cues to identify data that the necessary reasoning skills for the intended downstream application.
  arXiv  Detail & Related papers  (2024-02-06T19:18:04Z)
• Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes [57.62036621319563]
  We introduce CLLM, which leverages the prior knowledge of Large Language Models (LLMs) for data augmentation in the low-data regime. We demonstrate the superior performance of CLLM in the low-data regime compared to conventional generators.
  arXiv  Detail & Related papers  (2023-12-19T12:34:46Z)
• Generating Datasets with Pretrained Language Models [12.919486518128734]
  We show how large language models can be leveraged to obtain high-quality embeddings without requiring labeled data, finetuning or modifications to the pretraining objective. We utilize the generative abilities of PLMs to generate entire datasets of labeled text pairs from scratch, which can then be used for regular finetuning of much smaller models.
  arXiv  Detail & Related papers  (2021-04-15T15:51:41Z)

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.