用分布外代理提升模型在未知任务下的推理能力
Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval
- 通过构建分布外代理近似未知目标域，指导示范检索
- 在多个大模型和任务上显著提升分布外场景的鲁棒性
- 适合需要在不可访问数据上增强推理能力的研究者
尽管已有研究证明大型语言模型（LLMs）可在分布外（OOD）任务上表现良好，但随着分布偏移加剧，其优势会减弱。为提升推理能力，研究者尝试从源域中检索与目标分布相似且信息丰富的示范。然而，在目标域不可访问的实际场景中，评估未知分布极具挑战，进而影响示范选择质量。为此，本文提出DOPA框架，利用分布外代理近似不可访问的目标域，引导示范检索过程。基于代理评估，DOPA进一步引入基于马氏距离的全局多样性约束，确保所选示范具备充分多样性。在多个大模型和任务上的实验表明，DOPA能有效提升模型在分布外设置下的鲁棒性。
原文摘要 · Abstract (English)
Although studies have demonstrated that Large Language Models (LLMs) can perform well on Out-of-Distribution (OOD) tasks, their advantage tends to diminish as the distribution shift becomes more severe. Consequently, researchers aim to retrieve distributionally similar and informative demonstrations from the available source domain to boost the inference capabilities of LLMs. However, in practical scenarios where the target domain is inaccessible, evaluating the unknown distribution is challenging, which indirectly impacts the quality of the selected demonstrations. To address this problem, we propose \textbf{DOPA}, a demonstration search framework that incorporates an OOD proxy to approximate the inaccessible target domain and guide the retrieval process. Building on proxy-based evaluation, DOPA further introduces a Mahalanobis distance-based global diversity constraint to ensure sufficient diversity among the retrieved demonstrations. Experimental results on multiple LLMs and tasks demonstrate that DOPA effectively enhances robustness in OOD settings\footnote{https://github.com/bort64/ood\_code}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。