ORBIT：通过起源调控融合在生成式检索中保留基础语言能力

摘要

尽管大语言模型（LLM）开发取得了快速进展，但针对特定任务进行微调时，往往会导致其通用的基于语言的推理能力出现灾难性遗忘。本研究在生成式检索（GenRetrieval）任务背景下探究并应对这一挑战。我们发现，在生成式检索微调过程中，这种遗忘会迅速发生，且与微调后模型参数和原始模型参数之间的距离相关。基于这些观察，我们提出ORBIT，一种新颖的方法——它主动追踪微调后模型权重与初始模型权重之间的距离，并在生成式检索微调过程中，当该模型间距离超过最大阈值时，采用权重平均策略来约束模型漂移。结果表明，ORBIT在文本生成和检索性能上均优于常见的持续学习基线方法以及同样采用权重平均的相关正则化方法，有效保留了模型能力。

English

Despite the rapid advancements in large language model (LLM) development, fine-tuning them for specific tasks often results in the catastrophic forgetting of their general, language-based reasoning abilities. This work investigates and addresses this challenge in the context of the Generative Retrieval (GenRetrieval) task. During GenRetrieval fine-tuning, we find this forgetting occurs rapidly and correlates with the distance between the fine-tuned and original model parameters. Given these observations, we propose ORBIT, a novel approach that actively tracks the distance between fine-tuned and initial model weights, and uses a weight averaging strategy to constrain model drift during GenRetrieval fine-tuning when this inter-model distance exceeds a maximum threshold. Our results show that ORBIT retains substantial text and retrieval performance by outperforming both common continual learning baselines and related regularization methods that also employ weight averaging.

ORBIT：通过起源调控融合在生成式检索中保留基础语言能力

ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging

摘要

Support