Assessing "Implicit" Retrieval Robustness of Large Language Models

TL;DR

Evaluating the “implicit” retrieval robustness of various large language models 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.

Abstract

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.

Figures (5)

• Figure 1: Difference between explicitly and implicitly modelling the relevance of retrieved context. The explicit approach evaluates whether the retrieved context is relevant and then calls different functions based on this assessment. In contrast, the implicit approach directly generates the final answer in an end-to-end manner.
• Figure 2: Performance by Prompting different LLMs when provided with no context (None), gold context (Gold) and distracting context (Distract).
• Figure 3: Performance by fine-tuning LLMs with and without context. When fine-tuning without context, we also test without context (None). When fine-tuning with context, we use only gold context when fine-tuning, then testing on gold and distracting context (Gold and Distraction).
• Figure 4: Fine-tuning LLMs with varied distraction ratios and then testing on gold context. Incorporating distracting context during fine-tuning does not compromise performance when provided with gold context.
• Figure 5: Fine-tuning LLMs with varying distraction ratios (0%, 20% and 50%) and then testing on distracting contexts. Incorporating distracting context during fine-tuning significantly enhances retrieval robustness in distracting contexts. When the distraction ratio is increased to 50%, LLMs can achieve performance comparable to the upper-bound performance without retrieval.