Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning

This study presents a question-based knowledge encoding approach that improves retrieval-augmented generation (RAG) systems without requiring fine-tuning or traditional chunking. We encode textual content using generated questions that span the lexical and semantic space, creating targeted retrieval cues combined with a custom syntactic reranking method.In single-hop retrieval over 109 scientific papers, our approach achieves a Recall@3 of 0.84, outperforming traditional chunking methods by 60 percent. We also introduce "paper-cards", concise paper summaries under 300 characters, which enhance BM25 retrieval, increasing MRR@3 from 0.56 to 0.85 on simplified technical queries.For multihop tasks, our reranking method reaches an F1 score of 0.52 with LLaMA2-Chat-7B on the LongBench 2WikiMultihopQA dataset, surpassing chunking and fine-tuned baselines which score 0.328 and 0.412 respectively.This method eliminates fine-tuning requirements, reduces retrieval latency, enables intuitive question-driven knowledge access, and decreases vector storage demands by 80%, positioning it as a scalable and efficient RAG alternative.

@article{eponon2025_2506.13778,
  title={ Knowledge Compression via Question Generation: Enhancing Multihop Document Retrieval without Fine-tuning },
  author={ Anvi Alex Eponon and Moein Shahiki-Tash and Ildar Batyrshin and Christian E. Maldonado-Sifuentes and Grigori Sidorov and Alexander Gelbukh },
  journal={arXiv preprint arXiv:2506.13778},
  year={ 2025 }
}