Assessing "Implicit" Retrieval Robustness of Large Language Models
This addresses the issue of performance degradation due to irrelevant retrieved contexts in retrieval-augmented generation systems, offering an incremental improvement by eliminating the need for explicit relevance judgments.
The paper tackles the problem of retrieval robustness in large language models for retrieval-augmented generation, finding that fine-tuning on mixed gold and distracting contexts significantly enhances robustness to retrieval inaccuracies while maintaining accuracy with relevant context.
Retrieval-augmented generation has gained popularity as a framework to enhance large language models with external knowledge. However, its effectiveness hinges on the retrieval robustness of the model. If the model lacks retrieval robustness, its performance is constrained by the accuracy of the retriever, resulting in significant compromises when the retrieved context is irrelevant. In this paper, we evaluate the "implicit" retrieval robustness of various large language models, instructing them to directly output the final answer without explicitly judging the relevance of the retrieved context. Our findings reveal that fine-tuning on a mix of gold and distracting context significantly enhances the model's robustness to retrieval inaccuracies, while still maintaining its ability to extract correct answers when retrieval is accurate. This suggests that large language models can implicitly handle relevant or irrelevant retrieved context by learning solely from the supervision of the final answer in an end-to-end manner. Introducing an additional process for explicit relevance judgment can be unnecessary and disrupts the end-to-end approach.