Selecting Influential Samples for Long Context Alignment via Homologous Models’ Guidance and Contextual Awareness Measurement
Keywords: Long context alignment, Large language models, Data selection, Efficient instruction tuning
TL;DR: We design a novel data selection framework that effectively selects long instruction-following samples to achieve better long context alignment for large language models.
Abstract: The expansion of large language models to effectively handle instructions with extremely long contexts has yet to be fully investigated. The primary obstacle lies in constructing a high-quality long instruction-following dataset devised for long context alignment. Existing studies have attempted to scale up the available data volume by synthesizing long instruction-following samples. However, indiscriminately increasing the quantity of data without a well-defined strategy for ensuring data quality may introduce low-quality samples and restrict the final performance. To bridge this gap, we aim to address the unique challenge of long-context alignment, i.e., modeling the long-range dependencies for handling instructions and lengthy input contexts. We propose GATEAU, a novel framework designed to identify the influential and high-quality samples enriched with long-range dependency relations by utilizing crafted Homologous Models' Guidance (HMG) and Contextual Awareness Measurement (CAM). Specifically, HMG attempts to measure the difficulty of generating corresponding responses due to the long-range dependencies, using the perplexity scores of the response from two homologous models with different context windows. Also, the role of CAM is to measure the difficulty of understanding the long input contexts due to long-range dependencies by evaluating whether the model’s attention is focused on important segments. Built upon both proposed methods, we select the most challenging samples as the influential data to effectively frame the long-range dependencies, thereby achieving better performance of LLMs. Comprehensive experiments indicate that GATEAU effectively identifies samples enriched with long-range dependency relations and the model trained on these selected samples exhibits better instruction-following and long-context understanding capabilities.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
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.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
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: 935
Loading