Pith. sign in

REVIEW 19 cited by

FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.13576 v2 pith:ZEKEZLMX submitted 2024-05-22 cs.CL cs.IR

Jiajie Jin , Yutao Zhu , Guanting Dong , Yuyao Zhang , Xinyu Yang , Chenghao Zhang , Tong Zhao , Zhao Yang
show 2 more authors
Zhicheng Dou Ji-Rong Wen
This is my paper · ORCID
classification cs.CLcs.IR
keywords toolkitefficientframeworkmodelsmodularresearchersalgorithmsavailable
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

With the advent of large language models (LLMs) and multimodal large language models (MLLMs), the potential of retrieval-augmented generation (RAG) has attracted considerable research attention. Various novel algorithms and models have been introduced to enhance different aspects of RAG systems. However, the absence of a standardized framework for implementation, coupled with the inherently complex RAG process, makes it challenging and time-consuming for researchers to compare and evaluate these approaches in a consistent environment. Existing RAG toolkits, such as LangChain and LlamaIndex, while available, are often heavy and inflexibly, failing to meet the customization needs of researchers. In response to this challenge, we develop \ours{}, an efficient and modular open-source toolkit designed to assist researchers in reproducing and comparing existing RAG methods and developing their own algorithms within a unified framework. Our toolkit has implemented 16 advanced RAG methods and gathered and organized 38 benchmark datasets. It has various features, including a customizable modular framework, multimodal RAG capabilities, a rich collection of pre-implemented RAG works, comprehensive datasets, efficient auxiliary pre-processing scripts, and extensive and standard evaluation metrics. Our toolkit and resources are available at https://github.com/RUC-NLPIR/FlashRAG.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrieval

    cs.CL 2026-01 conditional novelty 6.0 of 10

    An evolving graph, refreshed at each retrieval step, anchors salient entities and relations and guides iterative retrieval and answer generation in RAG, improving multi-hop QA.

  2. TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework

    cs.IR 2025-11 conditional novelty 6.0 of 10

    TeaRAG shows that hybrid chunk+triplet retrieval with Personalized PageRank and an iterative process-aware DPO reward keeps QA accuracy while cutting reasoning tokens by roughly 60%.

  3. DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation

    cs.CR 2025-09 conditional novelty 6.0 of 10

    DCMI infers RAG database membership by subtracting the system's yes-probability on a perturbed query from the original query, cancelling the interference of non-member retrieved documents.

  4. HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving

    cs.DB 2025-07 conditional novelty 6.0 of 10

    HedraRAG uses a graph abstraction and dynamic transformations to pipeline generation and retrieval stages, achieving 1.5x to 5x speedups in heterogeneous RAG serving.

  5. Constructing and Evaluating Declarative RAG Pipelines in PyTerrier

    cs.IR 2025-06 conditional novelty 6.0 of 10

    PyTerrier-RAG extends PyTerrier with datatypes, readers, datasets, and metrics for building and evaluating declarative retrieval-augmented generation pipelines.

  6. Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification

    cs.AI 2025-06 conditional novelty 6.0 of 10

    A pair of reinforcement-learning-trained agents, one for reasoning and one for search, improves accuracy on multi-hop claim verification benchmarks.

  7. BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions

    cs.CL 2025-06 conditional novelty 6.0 of 10

    BioMol-MQA is a new multimodal QA dataset for polypharmacy in which LLMs perform poorly zero-shot but much better when given gold context.

  8. Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Tool-Star combines cold-start supervised fine-tuning with a multi-tool self-critic reinforcement learning algorithm and hierarchical rewards to improve LLM tool-use reasoning.

  9. SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration

    cs.AI 2026-07 conditional novelty 5.0 of 10

    A multi-agent web-search framework that stores progress in shared evidence, coverage, and failure state reports the best F1 scores among compared baselines on WideSearch (80.3 item F1) and GISA (76.5 set F1).

  10. RECON: Reasoning with Condensation for Efficient Retrieval-Augmented Generation

    cs.CL 2025-10 conditional novelty 5.0 of 10

    Placing a frozen, distilled summarizer between search and reasoning improves RL-RAG exact match (up to 14.5% relative on a 3B agent) while cutting context length by 35%.

  11. FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation

    cs.CL 2025-06 conditional novelty 5.0 of 10

    FlexRAG is a modular, open-source RAG framework with text, multimodal, and web retrieval, plus evaluation tools and efficient memory-mapped indexing.

  12. R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning

    cs.CL 2025-06 conditional novelty 5.0 of 10

    An RL framework for retrieval-augmented generation that rewards LLMs for well-timed searches, high-quality evidence, and final answers, improving multi-hop QA.

  13. ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A modular, verifier-driven RAG pipeline with iterative re-decomposition outperforms fine-tuned and agentic baselines on four multi-hop QA benchmarks.

  14. Removal of Hallucination on Hallucination: Debate-Augmented RAG

    cs.CL 2025-05 conditional novelty 5.0 of 10

    DRAG adds structured multi-agent debates to both the retrieval and generation stages of RAG, improving multi-hop QA accuracy while showing mixed single-hop results.

  15. Benchmarking Poisoning Attacks against Retrieval-Augmented Generation

    cs.CR 2025-05 conditional novelty 5.0 of 10

    A unified benchmark evaluation finds that existing RAG poisoning attacks remain effective on standard QA datasets, drop on expanded knowledge bases, and are only partially mitigated by current defenses.

  16. R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning

    cs.CL 2025-05 conditional novelty 5.0 of 10

    R1-Searcher++ uses SFT cold-start plus reinforcement learning with group and memorization rewards to teach Qwen-2.5-7B to balance internal knowledge and external retrieval, improving accuracy and reducing retrieval calls.

  17. Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization

    cs.CL 2025-05 reject novelty 5.0 of 10

    RoleRAG tunes only role-token embeddings on a frozen LLM to run six RAG sub-tasks, reporting improved QA accuracy, but with inconsistent headline numbers and no significance tests.

  18. KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language Models

    cs.AI 2025-06 reject novelty 4.0 of 10

    KunLunBaizeRAG reports improved exact-match and LLM-judged scores on four multi-hop QA benchmarks using a reinforcement-learning-driven RAG framework.

  19. Retrieval-Augmented Generation Systems for Intellectual Property via Synthetic Multi-Angle Fine-tuning

    cs.CL 2025-05 reject novelty 4.0 of 10

    The paper proposes MQG-RFM, which fine-tunes a patent retriever on LLM-generated query variations, and reports dramatic accuracy gains that are undercut by uncontrolled baseline comparisons and unverifiable numbers.

Pith tools