RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cofala, Tim, Astappiev, Oleh, Xion, William, Teklehaymanot, Hailay
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913986150137856
author Cofala, Tim
Astappiev, Oleh
Xion, William
Teklehaymanot, Hailay
author_facet Cofala, Tim
Astappiev, Oleh
Xion, William
Teklehaymanot, Hailay
contents Retrieval-Augmented Generation (RAG) enriches Large Language Models (LLMs) by combining their internal, parametric knowledge with external, non-parametric sources, with the goal of improving factual correctness and minimizing hallucinations. The LiveRAG 2025 challenge explores RAG solutions to maximize accuracy on DataMorgana's QA pairs, which are composed of single-hop and multi-hop questions. The challenge provides access to sparse OpenSearch and dense Pinecone indices of the Fineweb 10BT dataset. It restricts model use to LLMs with up to 10B parameters and final answer generation with Falcon-3-10B. A judge-LLM assesses the submitted answers along with human evaluators. By exploring distinct retriever combinations and RAG solutions under the challenge conditions, our final solution emerged using InstructRAG in combination with a Pinecone retriever and a BGE reranker. Our solution achieved a correctness score of 1.13 and a faithfulness score of 0.55 in the non-human evaluation, placing it overall in third place in the SIGIR 2025 LiveRAG Challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14412
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition
Cofala, Tim
Astappiev, Oleh
Xion, William
Teklehaymanot, Hailay
Information Retrieval
Artificial Intelligence
Machine Learning
Retrieval-Augmented Generation (RAG) enriches Large Language Models (LLMs) by combining their internal, parametric knowledge with external, non-parametric sources, with the goal of improving factual correctness and minimizing hallucinations. The LiveRAG 2025 challenge explores RAG solutions to maximize accuracy on DataMorgana's QA pairs, which are composed of single-hop and multi-hop questions. The challenge provides access to sparse OpenSearch and dense Pinecone indices of the Fineweb 10BT dataset. It restricts model use to LLMs with up to 10B parameters and final answer generation with Falcon-3-10B. A judge-LLM assesses the submitted answers along with human evaluators. By exploring distinct retriever combinations and RAG solutions under the challenge conditions, our final solution emerged using InstructRAG in combination with a Pinecone retriever and a BGE reranker. Our solution achieved a correctness score of 1.13 and a faithfulness score of 0.55 in the non-human evaluation, placing it overall in third place in the SIGIR 2025 LiveRAG Challenge.
title RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition
topic Information Retrieval
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.14412