Question-to-Question Retrieval for Hallucination-Free Knowledge Access: An Approach for Wikipedia and Wikidata Question Answering
This paper introduces an approach to question answering over knowledge bases like Wikipedia and Wikidata by performing "question-to-question" matching and retrieval from a dense vector embedding store. Instead of embedding document content, we generate a comprehensive set of questions for each logical content unit using an instruction-tuned LLM. These questions are vector-embedded and stored, mapping to the corresponding content. Vector embedding of user queries are then matched against this question vector store. The highest similarity score leads to direct retrieval of the associated article content, eliminating the need for answer generation. Our method achieves high cosine similarity ( > 0.9 ) for relevant question pairs, enabling highly precise retrieval. This approach offers several advantages including computational efficiency, rapid response times, and increased scalability. We demonstrate its effectiveness on Wikipedia and Wikidata, including multimedia content through structured fact retrieval from Wikidata, opening up new pathways for multimodal question answering.
Code (0)
등록된 구현이 없습니다.
Tasks
Answer GenerationComputational EfficiencyHallucinationQuestion AnsweringRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
LAG: Logic-Augmented Generation from a Cartesian Perspective
Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet exhibit critical limitations in knowledge-intensive tasks, often generating hallucinations when faced with question…
Semantic RetrievalFilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA
Visual Question Answering requires models to generate accurate answers by integrating visual and textual understanding. However, VQA models still struggle with hallucinations, producing convincing but incorrect answers, …
Question AnsweringRetrievalRetrieval-augmented GenerationVisual Question Answering+1Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
While reasoning in LLMs plays a natural role in math, code generation, and multi-hop factual questions, its effect on simple, single-hop factual questions remains unclear. Such questions do not require step-by-step logic…
Code GenerationJMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability
Large Language Models (LLMs) have demonstrated a remarkable potential in medical knowledge acquisition and question-answering. However, LLMs can potentially hallucinate and yield factually incorrect outcomes, even with d…
GPUInformation RetrievalMedical Question AnsweringQuestion Answering+3Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
Multimodal Retrieval Augmented Generation (mRAG) plays an important role in mitigating the "hallucination" issue inherent in multimodal large language models (MLLMs). Although promising, existing heuristic mRAGs typicall…
BenchmarkingHallucinationQuestion AnsweringRetrieval+3