A Unified Moral-Value Dataset for Instruction Tuning

• URL: http://arxiv.org/abs/2607.21279v1
• Date: Thu, 23 Jul 2026 12:57:03 GMT
• Title: A Unified Moral-Value Dataset for Instruction Tuning
• Abstract summary: How to align large language models (LLMs) to a particular set of human values is still an open problem.<n>Recent studies show that instruction tuning has strong potential for zero-shot tasks.<n>We construct a unified moral-value dataset that can be directly used for instruction tuning.
• Score: 2.97193551880289
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have developed rapidly and become valuable tools in everyday life. However, how to align LLMs to a particular set of human values is still an open problem. Recent studies show that instruction tuning has strong potential for zero-shot tasks and may serve as an effective approach to addressing value alignment. Nevertheless, although many datasets for instruction tuning already exist, they are not specifically designed around moral scenarios and behaviors. We construct a unified moral-value dataset that can be directly used for instruction tuning. This dataset is built upon existing moral-value datasets by merging them into a unified corpus and converting them into an instruction-response format. We show that training on a mixed dataset combining general task datasets with our dataset preserves general-task performance, and we report preliminary observations on how the mixing ratio affects value-oriented task performance. Our work provides a moral-value dataset for instruction tuning and offers a useful resource for further alignment research. The dataset is available at https://huggingface.co/datasets/teohzzh/value-for-instruction-tuning.

Related papers

• Convex Dataset Valuation for Post-Training [21.22512177964122]
  We propose a scalable convex dataset-level valuation method based on mean matching (KMM) in gradient space.<n>We show that our approach consistently outperforms existing valuation baselines, achieving stronger performance with low overhead.
  arXiv  Detail & Related papers  (2026-05-15T23:35:07Z)
• TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation [50.319535974012]
  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.
  arXiv  Detail & Related papers  (2025-06-30T15:45:28Z)
• Aligning Instruction Tuning with Pre-training [61.50161961371844]
  We propose Aligning Instruction Tuning with Pre-training (AITP) to align instruction tuning with pre-training distributions.<n>We show consistent performance improvements with AITP on three fully open large language models (LLMs) across eight benchmarks.
  arXiv  Detail & Related papers  (2025-01-16T08:27:40Z)
• Cookbook: A framework for improving LLM generative abilities via programmatic data generating templates [57.29125360837203]
  Cookbook is a framework that generates training data consisting of simple patterns over random tokens. We find that finetuning on Cookbook-generated data is able to improve performance on its corresponding task by up to 52.7 accuracy points.
  arXiv  Detail & Related papers  (2024-10-07T17:29:40Z)
• TAIA: Large Language Models are Out-of-Distribution Data Learners [30.57872423927015]
  We propose an effective inference-time intervention method: Training All parameters but Inferring with only Attention (trainallInfAttn) trainallInfAttn achieves superior improvements compared to both the fully fine-tuned model and the base model in most scenarios. The high tolerance of trainallInfAttn to data mismatches makes it resistant to jailbreaking tuning and enhances specialized tasks using general data.
  arXiv  Detail & Related papers  (2024-05-30T15:57:19Z)
• Less is More: High-value Data Selection for Visual Instruction Tuning [127.38740043393527]
  We propose a high-value data selection approach TIVE, to eliminate redundancy within the visual instruction data and reduce the training cost. Our approach using only about 15% data can achieve comparable average performance to the full-data fine-tuned model across eight benchmarks.
  arXiv  Detail & Related papers  (2024-03-14T16:47:25Z)
• Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation [9.574486521686323]
  Bonito is a model for conditional task generation that converts unannotated text into task-specific training datasets for instruction tuning. We show that Bonito significantly improves the average performance of pretrained and instruction tuned models over the de facto self supervised baseline.
  arXiv  Detail & Related papers  (2024-02-28T13:54:57Z)
• Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation [92.2167864437497]
  We propose Dynosaur, a dynamic growth paradigm for the automatic curation of instruction-tuning data. Based on the metadata of existing datasets, we use LLMs to automatically construct instruction-tuning data by identifying relevant data fields and generating appropriate instructions. By leveraging the existing annotated datasets, Dynosaur offers several advantages: 1) it reduces the API cost for generating instructions; 2) it provides high-quality data for instruction tuning; and 3) it supports the continuous improvement of models by generating instruction-tuning data when a new annotated dataset becomes available.
  arXiv  Detail & Related papers  (2023-05-23T17:56:26Z)
• A Data Fusion Framework for Multi-Domain Morality Learning [3.0671872389903547]
  We describe a data fusion framework for training on multiple heterogeneous datasets. The proposed framework achieves state-of-the-art performance in different datasets compared to prior works in morality inference.
  arXiv  Detail & Related papers  (2023-04-04T22:05:02Z)
• Intermediate Training on Question Answering Datasets Improves Generative Data Augmentation [32.83012699501051]
  We improve generative data augmentation by formulating the data generation as context generation task. We cast downstream tasks into question answering format and adapt the fine-tuned context generators to the target task domain. We demonstrate substantial improvements in performance in few-shot, zero-shot settings.
  arXiv  Detail & Related papers  (2022-05-25T09:28:21Z)
• How Useful is Self-Supervised Pretraining for Visual Tasks? [133.1984299177874]
  We evaluate various self-supervised algorithms across a comprehensive array of synthetic datasets and downstream tasks. Our experiments offer insights into how the utility of self-supervision changes as the number of available labels grows.
  arXiv  Detail & Related papers  (2020-03-31T16:03:22Z)

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.