Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2412.15443 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913620609204224 |
|---|---|
| author | Mahalingam, Aakash Gande, Vinesh Kumar Chadha, Aman Jain, Vinija Chaudhary, Divya |
| author_facet | Mahalingam, Aakash Gande, Vinesh Kumar Chadha, Aman Jain, Vinija Chaudhary, Divya |
| contents | Retrieval-Augmented Generation (RAG) systems have become pivotal in leveraging vast corpora to generate informed and contextually relevant responses, notably reducing hallucinations in Large Language Models. Despite significant advancements, these systems struggle to efficiently process and retrieve information from large datasets while maintaining a comprehensive understanding of the context. This paper introduces SKETCH, a novel methodology that enhances the RAG retrieval process by integrating semantic text retrieval with knowledge graphs, thereby merging structured and unstructured data for a more holistic comprehension. SKETCH, demonstrates substantial improvements in retrieval performance and maintains superior context integrity compared to traditional methods. Evaluated across four diverse datasets: QuALITY, QASPER, NarrativeQA, and Italian Cuisine-SKETCH consistently outperforms baseline approaches on key RAGAS metrics such as answer_relevancy, faithfulness, context_precision and context_recall. Notably, on the Italian Cuisine dataset, SKETCH achieved an answer relevancy of 0.94 and a context precision of 0.99, representing the highest performance across all evaluated metrics. These results highlight SKETCH's capability in delivering more accurate and contextually relevant responses, setting new benchmarks for future retrieval systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_15443 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval Mahalingam, Aakash Gande, Vinesh Kumar Chadha, Aman Jain, Vinija Chaudhary, Divya Computation and Language Retrieval-Augmented Generation (RAG) systems have become pivotal in leveraging vast corpora to generate informed and contextually relevant responses, notably reducing hallucinations in Large Language Models. Despite significant advancements, these systems struggle to efficiently process and retrieve information from large datasets while maintaining a comprehensive understanding of the context. This paper introduces SKETCH, a novel methodology that enhances the RAG retrieval process by integrating semantic text retrieval with knowledge graphs, thereby merging structured and unstructured data for a more holistic comprehension. SKETCH, demonstrates substantial improvements in retrieval performance and maintains superior context integrity compared to traditional methods. Evaluated across four diverse datasets: QuALITY, QASPER, NarrativeQA, and Italian Cuisine-SKETCH consistently outperforms baseline approaches on key RAGAS metrics such as answer_relevancy, faithfulness, context_precision and context_recall. Notably, on the Italian Cuisine dataset, SKETCH achieved an answer relevancy of 0.94 and a context precision of 0.99, representing the highest performance across all evaluated metrics. These results highlight SKETCH's capability in delivering more accurate and contextually relevant responses, setting new benchmarks for future retrieval systems. |
| title | SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrieval |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.15443 |