Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration
Keywords: data synthesis, preference learning, LLM alignment
TL;DR: We present a novel approach for automatically generating effective training samples from the target model's failure cases by optimizing another model to create samples via iterative preference learning.
Abstract: Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data, leading to impressive performance across a range of downstream applications. Current methods often rely on human-annotated data or predefined task templates to direct powerful LLMs in synthesizing task-relevant data for effective model training. However, this dependence on manually designed components may constrain the scope of generated data, potentially overlooking critical edge cases or novel scenarios that could challenge the model. In this paper, we present a novel approach, ReverseGen, designed to automatically generate effective training samples that expose the weaknesses of LLMs. Specifically, we introduce a dedicated proposer trained to produce queries that lead target models to generate unsatisfactory responses. These failure-inducing queries are then used to construct training data, helping to address the models' shortcomings and improve overall performance. Our approach is flexible and can be applied to models of various scales (3B, 7B, and 8B). We evaluate ReverseGen on three key applications—safety, honesty, and math—demonstrating that our generated data is both highly effective and diverse. Models fine-tuned with ReverseGen-generated data consistently outperform those trained on human-annotated or general model-generated data, offering a new perspective on data synthesis for task-specific LLM enhancement.
Primary Area: applications to computer vision, audio, language, and other modalities
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8852
Loading