IRLGDec 17, 2024

Boosting LLM-based Relevance Modeling with Distribution-Aware Robust Learning

arXiv:2412.12504v15 citationsh-index: 5CIKM
Originality Incremental advance
AI Analysis

This addresses relevance modeling challenges for search engines like Alipay, offering an incremental improvement over existing LLM fine-tuning approaches.

The paper tackles the problem of LLM-based relevance modeling struggling with fine-grained relevance distinctions and data distribution shifts in search engines, proposing a Distribution-Aware Robust Learning framework (DaRL) that improves performance by 15% in offline metrics and has been deployed in Alipay's insurance product search.

With the rapid advancement of pre-trained large language models (LLMs), recent endeavors have leveraged the capabilities of LLMs in relevance modeling, resulting in enhanced performance. This is usually done through the process of fine-tuning LLMs on specifically annotated datasets to determine the relevance between queries and items. However, there are two limitations when LLMs are naively employed for relevance modeling through fine-tuning and inference. First, it is not inherently efficient for performing nuanced tasks beyond simple yes or no answers, such as assessing search relevance. It may therefore tend to be overconfident and struggle to distinguish fine-grained degrees of relevance (e.g., strong relevance, weak relevance, irrelevance) used in search engines. Second, it exhibits significant performance degradation when confronted with data distribution shift in real-world scenarios. In this paper, we propose a novel Distribution-Aware Robust Learning framework (DaRL) for relevance modeling in Alipay Search. Specifically, we design an effective loss function to enhance the discriminability of LLM-based relevance modeling across various fine-grained degrees of query-item relevance. To improve the generalizability of LLM-based relevance modeling, we first propose the Distribution-Aware Sample Augmentation (DASA) module. This module utilizes out-of-distribution (OOD) detection techniques to actively select appropriate samples that are not well covered by the original training set for model fine-tuning. Furthermore, we adopt a multi-stage fine-tuning strategy to simultaneously improve in-distribution (ID) and OOD performance, bridging the performance gap between them. DaRL has been deployed online to serve the Alipay's insurance product search...

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes