Enhancing Robustness of Retrieval-Augmented Language Models with In-Context Learning
This work addresses robustness issues in RALMs for open-domain QA, offering an incremental improvement by enhancing reasoning capabilities in imperfect retrieval scenarios.
The study tackled the problem of Retrieval-Augmented Language Models (RALMs) struggling with unanswerable queries and conflicting information in open-domain question answering by introducing an in-context learning approach using Machine Reading Comprehension demonstrations, which increased accuracy in identifying such scenarios without additional fine-tuning.
Retrieval-Augmented Language Models (RALMs) have significantly improved performance in open-domain question answering (QA) by leveraging external knowledge. However, RALMs still struggle with unanswerable queries, where the retrieved contexts do not contain the correct answer, and with conflicting information, where different sources provide contradictory answers due to imperfect retrieval. This study introduces an in-context learning-based approach to enhance the reasoning capabilities of RALMs, making them more robust in imperfect retrieval scenarios. Our method incorporates Machine Reading Comprehension (MRC) demonstrations, referred to as cases, to boost the model's capabilities to identify unanswerabilities and conflicts among the retrieved contexts. Experiments on two open-domain QA datasets show that our approach increases accuracy in identifying unanswerable and conflicting scenarios without requiring additional fine-tuning. This work demonstrates that in-context learning can effectively enhance the robustness of RALMs in open-domain QA tasks.