BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering

2024/02/16 by Haoyu Wang, Wang, Haoyu, Li, Ruirui +8 · 8 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2402.11129

openalex publication_date 2024/02/16 · openalex created_date 2024/02/22 · openalex updated_date 2026/08/01

Abstract

Retrieval-augmented Large Language Models (LLMs) offer substantial benefits in enhancing performance across knowledge-intensive scenarios. However, these methods often face challenges with complex inputs and encounter difficulties due to noisy knowledge retrieval, notably hindering model effectiveness. To address this issue, we introduce BlendFilter, a novel approach that elevates retrieval-augmented LLMs by integrating query generation blending with knowledge filtering. BlendFilter proposes the blending process through its query generation method, which integrates both external and internal knowledge augmentation with the original query, ensuring comprehensive information gathering. Additionally, our distinctive knowledge filtering module capitalizes on the intrinsic capabilities of the LLM, effectively eliminating extraneous data. We conduct extensive experiments on three open-domain question answering benchmarks, and the findings clearly indicate that our innovative BlendFilter surpasses state-of-the-art baselines significantly.

Cited by

• In-Context Compositional Learning via Sparse Coding Transformer
• AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
• Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval
• Test-time Corpus Feedback: From Retrieval to RAG
• CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy
• RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation
• Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering
• REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing

Related

• MMKB-RAG: A Multi-Modal Knowledge-Based Retrieval-Augmented Generation Framework
• RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation
• Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation
• Retrieval-Augmented Generation for Large Language Models: A Survey
• A Survey on Knowledge-Oriented Retrieval-Augmented Generation