LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge

• URL: http://arxiv.org/abs/2509.08596v1
• Date: Wed, 10 Sep 2025 13:50:49 GMT
• Title: LLM Ensemble for RAG: Role of Context Length in Zero-Shot Question Answering for BioASQ Challenge
• Authors: Dima Galat, Diego Molla-Aliod,
• Abstract summary: Large language models (LLMs) can be used for information retrieval.<n> ensembles of zero-shot models can accomplish state-of-the-art performance on a domain-specific Yes/No QA task.
• Score: 0.03437656066916039
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Biomedical question answering (QA) poses significant challenges due to the need for precise interpretation of specialized knowledge drawn from a vast, complex, and rapidly evolving corpus. In this work, we explore how large language models (LLMs) can be used for information retrieval (IR), and an ensemble of zero-shot models can accomplish state-of-the-art performance on a domain-specific Yes/No QA task. Evaluating our approach on the BioASQ challenge tasks, we show that ensembles can outperform individual LLMs and in some cases rival or surpass domain-tuned systems - all while preserving generalizability and avoiding the need for costly fine-tuning or labeled data. Our method aggregates outputs from multiple LLM variants, including models from Anthropic and Google, to synthesize more accurate and robust answers. Moreover, our investigation highlights a relationship between context length and performance: while expanded contexts are meant to provide valuable evidence, they simultaneously risk information dilution and model disorientation. These findings emphasize IR as a critical foundation in Retrieval-Augmented Generation (RAG) approaches for biomedical QA systems. Precise, focused retrieval remains essential for ensuring LLMs operate within relevant information boundaries when generating answers from retrieved documents. Our results establish that ensemble-based zero-shot approaches, when paired with effective RAG pipelines, constitute a practical and scalable alternative to domain-tuned systems for biomedical question answering.

Related papers

• Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
  Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
  arXiv  Detail & Related papers  (2025-12-23T08:14:44Z)
• DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router [57.28685457991806]
  DeepSieve is an agentic RAG framework that incorporates information sieving via LLM-as-a-knowledge-router.<n>Our design emphasizes modularity, transparency, and adaptability, leveraging recent advances in agentic system design.
  arXiv  Detail & Related papers  (2025-07-29T17:55:23Z)
• Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
  Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
  arXiv  Detail & Related papers  (2025-07-13T03:29:41Z)
• BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions [22.805931447412668]
  BioMol-MQA dataset is composed of two parts (i) a multimodal knowledge graph (KG) with text and molecular structure for information retrieval; and (ii) challenging questions designed to test LLM capabilities in retrieving and reasoning over multimodal KG to answer questions.<n>Our benchmarks indicate that existing LLMs struggle to answer these questions and do well only when given the necessary background data, signaling the necessity for strong RAG frameworks.
  arXiv  Detail & Related papers  (2025-06-06T05:48:22Z)
• RAG-Enhanced Collaborative LLM Agents for Drug Discovery [28.025359322895905]
  CLADD is a retrieval-augmented generation (RAG)-empowered agentic system tailored to drug discovery tasks.<n>We show that it outperforms general-purpose and domain-specific LLMs as well as traditional deep learning approaches.
  arXiv  Detail & Related papers  (2025-02-22T00:12:52Z)
• On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems [5.69361786082969]
  Retrieval-augmented generation (RAG) has emerged as an approach to augment large language models (LLMs)<n>We evaluate various context sizes, BM25 and semantic search as retrievers, and eight base LLMs.<n>Our findings indicate that final QA performance improves steadily with up to 15 snippets but stagnates or declines beyond that.
  arXiv  Detail & Related papers  (2025-02-20T17:34:34Z)
• Knowledge Hierarchy Guided Biological-Medical Dataset Distillation for Domain LLM Training [10.701353329227722]
  We propose a framework that automates the distillation of high-quality textual training data from the extensive scientific literature.<n>Our approach self-evaluates and generates questions that are more closely aligned with the biomedical domain.<n>Our approach substantially improves question-answering tasks compared to pre-trained models from the life sciences domain.
  arXiv  Detail & Related papers  (2025-01-25T07:20:44Z)
• Comprehensive and Practical Evaluation of Retrieval-Augmented Generation Systems for Medical Question Answering [70.44269982045415]
  Retrieval-augmented generation (RAG) has emerged as a promising approach to enhance the performance of large language models (LLMs) We introduce Medical Retrieval-Augmented Generation Benchmark (MedRGB) that provides various supplementary elements to four medical QA datasets. Our experimental results reveals current models' limited ability to handle noise and misinformation in the retrieved documents.
  arXiv  Detail & Related papers  (2024-11-14T06:19:18Z)
• LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction [13.965777046473885]
  Large Language Models (LLMs) are increasingly adopted for applications in healthcare.<n>They reach the performance of domain experts on tasks such as question answering and document summarisation.<n>It is unclear how well LLMs perform on tasks that are traditionally pursued in the biomedical domain.
  arXiv  Detail & Related papers  (2024-08-22T09:37:40Z)
• SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation [50.26966969163348]
  Large Language Models (LLMs) have shown great potential in the biomedical domain with the advancement of retrieval-augmented generation (RAG) Existing retrieval-augmented approaches face challenges in addressing diverse queries and documents, particularly for medical knowledge queries. We propose Self-Rewarding Tree Search (SeRTS) based on Monte Carlo Tree Search (MCTS) and a self-rewarding paradigm.
  arXiv  Detail & Related papers  (2024-06-17T06:48:31Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.