Who's Who: Large Language Models Meet Knowledge Conflicts in Practice
This addresses a practical challenge in RAG systems for users needing reliable information, but it is incremental as it focuses on benchmarking existing models rather than proposing new solutions.
The paper tackles the problem of knowledge conflicts in retrieval-augmented generation (RAG) by introducing WhoQA, a benchmark dataset with 5K questions across 13 Wikidata property types and 150K entities, showing that conflicts degrade LLM performance in RAG settings.
Retrieval-augmented generation (RAG) methods are viable solutions for addressing the static memory limits of pre-trained language models. Nevertheless, encountering conflicting sources of information within the retrieval context is an inevitable practical challenge. In such situations, the language models are recommended to transparently inform users about the conflicts rather than autonomously deciding what to present based on their inherent biases. To analyze how current large language models (LLMs) align with our recommendation, we introduce WhoQA, a public benchmark dataset to examine model's behavior in knowledge conflict situations. We induce conflicts by asking about a common property among entities having the same name, resulting in questions with up to 8 distinctive answers. WhoQA evaluation set includes 5K questions across 13 Wikidata property types and 150K Wikipedia entities. Our experiments show that despite the simplicity of WhoQA questions, knowledge conflicts significantly degrades LLMs' performance in RAG settings.