Aligning Large Language Models via Fully Self-Synthetic Data

• URL: http://arxiv.org/abs/2510.06652v1
• Date: Wed, 08 Oct 2025 05:07:45 GMT
• Title: Aligning Large Language Models via Fully Self-Synthetic Data
• Authors: Shangjian Yin, Zhepei Wei, Xinyu Zhu, Wei-Lin Chen, Yu Meng,
• Abstract summary: Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets.<n>In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework for LLM alignment.<n>Experiments demonstrate that SAO effectively enhances the model's chat capabilities on standard benchmarks like AlpacaEval2.0.
• Score: 20.05693955243206
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets, while Reinforcement Learning from AI Feedback (RLAIF) also incurs significant costs, requiring the collection of diverse prompts and corresponding responses, often necessitating external reward models or proprietary models like GPT-4 to annotate preference pairs. In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework for LLM alignment, where all training data, including prompts (i.e., user queries), responses, and preferences, are generated by the model itself. Specifically, SAO first instructs the LLM to engage in persona role-play and generate diverse prompts and responses, which are then self-evaluated for preference optimization. Extensive experiments demonstrate that SAO effectively enhances the model's chat capabilities on standard benchmarks like AlpacaEval~2.0, while maintaining strong performance on downstream objective tasks (e.g., question-answering, math reasoning). Our work provides a practical solution for self-improvement in aligning LLMs, and the code for reproducing our results is available at: https://github.com/SJY8460/SAO.

Related papers

• FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users [111.56469697145519]
  We propose Few-Shot Preference Optimization, which reframes reward modeling as a meta-learning problem.<n>Under this framework, an LLM learns to quickly adapt to a user via a few labeled preferences from that user, constructing a personalized reward function for them.<n>We generate over 1M synthetic personalized preferences using publicly available LLMs.<n>We evaluate FSPO on personalized open-ended generation for up to 1,500 synthetic users across three domains: movie reviews, pedagogical adaptation based on educational background, and general question answering, along with a controlled human study.
  arXiv  Detail & Related papers  (2025-02-26T17:08:46Z)
• Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
  Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data. We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
  arXiv  Detail & Related papers  (2024-10-22T06:43:28Z)
• Self-Boosting Large Language Models with Synthetic Preference Data [97.94185115047999]
  We introduce SynPO, a self-boosting paradigm that leverages synthetic preference data for model alignment. After four SynPO iterations, Llama3-8B and Mistral-7B show significant enhancements in instruction-following abilities. SynPO improves the general performance of LLMs on various tasks, validated by a 3.2 to 5.0 average score increase on the well-recognized Open LLM leaderboard.
  arXiv  Detail & Related papers  (2024-10-09T14:57:31Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)
• Enabling Language Models to Implicitly Learn Self-Improvement [49.16868302881804]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. We propose an ImPlicit Self-ImprovemenT (PIT) framework that implicitly learns the improvement goal from human preference data.
  arXiv  Detail & Related papers  (2023-10-02T04:29:40Z)
• Aligning Large Language Models through Synthetic Feedback [43.84431341195111]
  We propose a novel alignment learning framework with synthetic feedback not dependent on extensive human annotations. In human evaluation, our model is preferred to Alpaca and Dolly-v2, 55.0% and 58.5% of the time, respectively.
  arXiv  Detail & Related papers  (2023-05-23T06:41:16Z)

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.