How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge

• URL: http://arxiv.org/abs/2602.10210v1
• Date: Tue, 10 Feb 2026 19:04:01 GMT
• Title: How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
• Abstract summary: HybridRAG-Bench is a framework for constructing benchmarks to evaluate retrieval-intensive, multi-hop reasoning over hybrid knowledge.<n>We show that HybridRAG-Bench rewards genuine retrieval and reasoning rather than parametric recall, offering a principled testbed for evaluating hybrid knowledge-augmented reasoning systems.
• Score: 26.8497597881469
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) continue to struggle with knowledge-intensive questions that require up-to-date information and multi-hop reasoning. Augmenting LLMs with hybrid external knowledge, such as unstructured text and structured knowledge graphs, offers a promising alternative to costly continual pretraining. As such, reliable evaluation of their retrieval and reasoning capabilities becomes critical. However, many existing benchmarks increasingly overlap with LLM pretraining data, which means answers or supporting knowledge may already be encoded in model parameters, making it difficult to distinguish genuine retrieval and reasoning from parametric recall. We introduce HybridRAG-Bench, a framework for constructing benchmarks to evaluate retrieval-intensive, multi-hop reasoning over hybrid knowledge. HybridRAG-Bench automatically couples unstructured text and structured knowledge graph representations derived from recent scientific literature on arXiv, and generates knowledge-intensive question-answer pairs grounded in explicit reasoning paths. The framework supports flexible domain and time-frame selection, enabling contamination-aware and customizable evaluation as models and knowledge evolve. Experiments across three domains (artificial intelligence, governance and policy, and bioinformatics) demonstrate that HybridRAG-Bench rewards genuine retrieval and reasoning rather than parametric recall, offering a principled testbed for evaluating hybrid knowledge-augmented reasoning systems. We release our code and data at github.com/junhongmit/HybridRAG-Bench.

Related papers

• Knowledge Capsules: Structured Nonparametric Memory Units for LLMs [0.6524460254566904]
  Large language models (LLMs) encode knowledge in parametric weights, making it costly to update or extend without retraining.<n>Retrieval-augmented generation (RAG) mitigates this limitation by appending retrieved text to the input, but operates purely through context expansion.<n>We propose Knowledge Capsules, structured nonparametric memory units that represent normalized relational knowledge.
  arXiv  Detail & Related papers  (2026-04-22T12:21:00Z)
• 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)
• RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning [69.87510139069218]
  Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs)<n>Recent progress has advanced text-based RAG to multi-turn reasoning through Reinforcement Learning (RL)<n>We introduce model, an RL-based framework that enables LLMs to perform multi-turn and adaptive graph-text hybrid RAG.
  arXiv  Detail & Related papers  (2025-12-10T10:05:31Z)
• KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues [58.305425399644086]
  Multi-Turn Long-Form Question Answering (MT-LFQA) is a key application paradigm of Large Language Models (LLMs) in knowledge-intensive domains.<n>We introduce textbfKnowMT-Bench, the textitfirst-ever benchmark designed to systematically evaluate MT-LFQA for LLMs across knowledge-intensive fields.
  arXiv  Detail & Related papers  (2025-09-26T04:32:29Z)
• Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation [89.65955788873532]
  Open-domain question answering (OpenQA) represents a cornerstone in natural language processing (NLP)<n>We propose a novel framework named GenKI, which aims to improve the OpenQA performance by exploring Knowledge Integration and controllable Generation.
  arXiv  Detail & Related papers  (2025-05-26T08:18:33Z)
• Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement [22.386864304549285]
  Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources and incorporating them into the context.<n>We propose Dynamic Parametric RAG (DyPRAG), a novel framework that leverages a lightweight parameter translator model to efficiently convert documents into parametric knowledge.
  arXiv  Detail & Related papers  (2025-03-31T09:46:35Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering [33.89497991289916]
  We propose a novel rewriting method CoTKR, Chain-of-Thought Enhanced Knowledge Rewriting, for generating reasoning traces and corresponding knowledge in an interleaved manner.<n>We conduct experiments using various Large Language Models (LLMs) across several Knowledge Graph Question Answering (KGQA) benchmarks.
  arXiv  Detail & Related papers  (2024-09-29T16:08:45Z)
• Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context [4.1229332722825]
  This paper introduces a novel framework that combines graph-driven context retrieval in conjunction to knowledge graphs based enhancement. We conduct experiments on various Large Language Models (LLMs) with different parameter sizes to evaluate their ability to ground knowledge and determine factual accuracy in answers to open-ended questions. Our methodology GraphContextGen consistently outperforms dominant text-based retrieval systems, demonstrating its robustness and adaptability to a larger number of use cases.
  arXiv  Detail & Related papers  (2024-01-23T11:25:34Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• 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.