pith. sign in

arxiv: 2410.05779 · v3 · submitted 2024-10-08 · 💻 cs.IR · cs.AI

LightRAG: Simple and Fast Retrieval-Augmented Generation

Zirui Guo , Lianghao Xia , Yanhua Yu , Tu Ao , Chao Huang This is my paper

Pith reviewed 2026-05-13 01:55 UTC · model grok-4.3

classification 💻 cs.IR cs.AI
keywords retrieval-augmented generationgraph structuresdual-level retrievalincremental updateslarge language modelsinformation retrievalcontextual awareness
0
0 comments X

The pith

LightRAG incorporates graph structures into retrieval-augmented generation to improve accuracy, efficiency, and contextual awareness in LLM responses.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes LightRAG as a new framework for retrieval-augmented generation that addresses limitations in existing systems by using graph structures for text indexing and retrieval. It introduces a dual-level retrieval system to capture both low-level and high-level knowledge, along with incremental updates for changing data. A sympathetic reader would care because this could lead to more reliable and faster AI systems that handle complex information dependencies better than flat vector-based approaches.

Core claim

LightRAG integrates graph structures into the indexing and retrieval processes of RAG systems, employing a dual-level retrieval mechanism that combines low-level and high-level knowledge discovery, and supports incremental updates to maintain performance in dynamic environments, resulting in improved retrieval accuracy and efficiency as validated by experiments.

What carries the argument

The dual-level retrieval system combined with graph structures for entity and relationship retrieval, which works by enhancing comprehensive information capture and efficient related entity lookup.

Load-bearing premise

That incorporating graph structures and a dual-level retrieval system will consistently enhance contextual awareness and response quality without creating new issues in varied and evolving data settings.

What would settle it

An experiment where LightRAG shows no significant improvement or lower performance than baseline RAG methods on standard benchmarks for retrieval accuracy or response quality.

read the original abstract

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs. However, existing RAG systems have significant limitations, including reliance on flat data representations and inadequate contextual awareness, which can lead to fragmented answers that fail to capture complex inter-dependencies. To address these challenges, we propose LightRAG, which incorporates graph structures into text indexing and retrieval processes. This innovative framework employs a dual-level retrieval system that enhances comprehensive information retrieval from both low-level and high-level knowledge discovery. Additionally, the integration of graph structures with vector representations facilitates efficient retrieval of related entities and their relationships, significantly improving response times while maintaining contextual relevance. This capability is further enhanced by an incremental update algorithm that ensures the timely integration of new data, allowing the system to remain effective and responsive in rapidly changing data environments. Extensive experimental validation demonstrates considerable improvements in retrieval accuracy and efficiency compared to existing approaches. We have made our LightRAG open-source and available at the link: https://github.com/HKUDS/LightRAG

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 3 minor

Summary. The paper proposes LightRAG, a RAG framework that augments standard vector-based retrieval with graph structures for indexing and retrieval, a dual-level (low- and high-level) retrieval mechanism, and an incremental update algorithm intended to support timely integration of new data in dynamic environments. It claims that these components together yield considerable gains in retrieval accuracy and efficiency relative to prior RAG systems, supported by experimental validation on multiple benchmarks, and releases the implementation as open source.

Significance. If the empirical results hold after the requested clarifications, the work would provide a practical, lightweight way to combine graph and vector representations for better handling of entity relationships while adding support for incremental updates—an under-explored aspect in current RAG literature. The open-source release is a clear strength that enables direct reproducibility and follow-on work.

major comments (2)
  1. [Experiments section] Experiments section: the reported results use standard static benchmarks with one-time indexing. No ablation or sequential-update experiments are presented that track retrieval accuracy, latency, or failure modes after each incremental document addition; this leaves the central claim about responsiveness in rapidly changing data environments untested and potentially overstated.
  2. [§3.2] §3.2 (Dual-level Retrieval): the description of how low-level and high-level retrieval results are fused (e.g., scoring, deduplication, or context assembly) is high-level and lacks pseudocode or precise algorithmic steps. Without this, it is impossible to verify whether the claimed improvement in contextual awareness is due to the graph component or to other unstated heuristics.
minor comments (3)
  1. [Abstract] Abstract: the phrase 'considerable improvements' is used without any numeric deltas, baseline names, or dataset identifiers; adding a single sentence with key metrics would make the claim immediately evaluable.
  2. [Figure 2] Figure 2 and §4.1: axis labels and legend entries are too small to read in the provided PDF rendering; increasing font size and adding a caption that explicitly states what each curve represents would improve clarity.
  3. [Related Work] Related Work: several recent graph-RAG papers (e.g., GraphRAG, HippoRAG) are cited only in passing; a short comparison table highlighting differences in indexing cost and update mechanism would strengthen the positioning.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments and for recognizing the potential of LightRAG. We address each major comment point by point below and describe the revisions we will make.

read point-by-point responses

  1. Referee: [Experiments section] Experiments section: the reported results use standard static benchmarks with one-time indexing. No ablation or sequential-update experiments are presented that track retrieval accuracy, latency, or failure modes after each incremental document addition; this leaves the central claim about responsiveness in rapidly changing data environments untested and potentially overstated.

    Authors: We agree that the current experiments rely on standard static benchmarks with one-time indexing and do not include sequential-update ablations that track accuracy, latency, or failure modes after successive document additions. While the incremental update algorithm is formally described in Section 4 (including its design for efficient, non-reindexing updates), the empirical validation of its behavior in dynamic settings is indeed absent. In the revised manuscript we will add a new set of sequential-update experiments on at least two benchmarks, reporting retrieval accuracy, latency, and any observed failure modes after each incremental addition. These results will directly support the claims regarding responsiveness in rapidly changing environments. revision: yes

  2. Referee: [§3.2] §3.2 (Dual-level Retrieval): the description of how low-level and high-level retrieval results are fused (e.g., scoring, deduplication, or context assembly) is high-level and lacks pseudocode or precise algorithmic steps. Without this, it is impossible to verify whether the claimed improvement in contextual awareness is due to the graph component or to other unstated heuristics.

    Authors: We acknowledge that Section 3.2 currently presents the dual-level retrieval and fusion process at a conceptual level without pseudocode or fine-grained algorithmic steps for scoring, deduplication, and context assembly. This makes it difficult to isolate the contribution of the graph structures. In the revised version we will expand §3.2 with a precise description of the fusion procedure, including the scoring function, deduplication criteria, and context-assembly logic, accompanied by pseudocode. The added detail will explicitly show how the graph-based low- and high-level results are combined and will clarify that the observed gains stem from the graph augmentation rather than unstated heuristics. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical systems proposal without derivation chain

full rationale

The paper presents LightRAG as an engineering framework combining graph indexing, dual-level retrieval, and an incremental update algorithm, validated through experiments on retrieval accuracy and efficiency. No equations, fitted parameters, or mathematical derivations appear in the provided text or abstract that reduce any claimed result to an input by construction. The incremental update is described as an algorithmic capability for dynamic environments but is not shown to be tautological with any fitted quantity or self-citation. Central claims rest on experimental comparisons rather than self-referential definitions or uniqueness theorems imported from prior author work. This is a standard empirical systems contribution whose validity is independent of any internal reduction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is an applied engineering paper; no free parameters, mathematical axioms, or postulated entities are introduced in the abstract.

pith-pipeline@v0.9.0 · 5499 in / 1040 out tokens · 43105 ms · 2026-05-13T01:55:07.190118+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 47 Pith papers

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

  1. Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration

    cs.CR 2026-05 unverdicted novelty 8.0

    Trojan Hippo attacks on LLM agent memory achieve 85-100% success rates in data exfiltration across four memory backends even after 100 benign sessions, while evaluated defenses reduce success rates but impose varying ...

  2. DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning

    cs.CL 2026-05 unverdicted novelty 7.0

    DeepRefine refines agent-compiled knowledge bases via multi-turn abductive diagnosis and RL training with a GBD reward, yielding consistent downstream task gains.

  3. SEM-RAG: Structure-Preserving Multimodal Graph Compilation and Entropy-Guided Retrieval for Telecommunication Standards

    eess.SP 2026-05 unverdicted novelty 7.0

    SEM-RAG compiles telecommunication standards into structure-preserving graphs and uses entropy-guided retrieval to reach 94.1% accuracy on TeleQnA and 93.8% on ORAN-Bench-13K while reducing indexing token usage compar...

  4. XGRAG: A Graph-Native Framework for Explaining KG-based Retrieval-Augmented Generation

    cs.AI 2026-04 unverdicted novelty 7.0

    XGRAG uses graph perturbations to quantify component contributions in GraphRAG and achieves 14.81% better explanation quality than text-based baselines on QA datasets, with correlations to graph centrality.

  5. OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving

    cs.CL 2026-04 unverdicted novelty 7.0

    OptiVerse is a new benchmark spanning neglected optimization domains that shows LLMs suffer sharp accuracy drops on hard problems due to modeling and logic errors, with a Dual-View Auditor Agent proposed to improve pe...

  6. Structure Guided Retrieval-Augmented Generation for Factual Queries

    cs.IR 2026-04 unverdicted novelty 7.0

    SG-RAG frames retrieval as subgraph matching to ensure LLMs meet every condition in factual queries and reports large gains over baselines on a new 120k-pair ERQA dataset.

  7. DOTRAG: Retrieval-Time Reasoning Along Paths

    cs.IR 2026-04 unverdicted novelty 7.0

    DotRAG reformulates graph retrieval as query-guided path reasoning with Division of Thought, reporting SOTA results on MetaQA and UltraDomain for multi-hop tasks.

  8. Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems

    cs.IR 2026-04 unverdicted novelty 7.0

    Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.

  9. GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning

    cs.AI 2026-03 unverdicted novelty 7.0

    GraphScout trains LLMs to autonomously synthesize structured training data from knowledge graphs via flexible exploration tools, enabling a 4B model to outperform larger LLMs by 16.7% on average with fewer inference t...

  10. AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation

    cs.IR 2026-02 unverdicted novelty 7.0

    AtomicRAG replaces chunk-based and triple-based GraphRAG with atom-entity graphs that store facts as atomic units and use personalized PageRank plus relevance filtering to achieve higher retrieval accuracy and reasoni...

  11. mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA

    cs.CV 2025-08 unverdicted novelty 7.0

    mKG-RAG constructs multimodal KGs via MLLM-driven extraction and vision-text matching then applies dual-stage query-aware retrieval to achieve new state-of-the-art results on knowledge-based VQA.

  12. SeedER: Seed-and-Expand Retrieval from Knowledge Graphs

    cs.LG 2026-05 unverdicted novelty 6.0

    SeedER uses initial dense seeding followed by RL-driven selective expansion to improve recall on compositional KG queries while limiting candidate set size.

  13. Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables

    cs.AI 2026-05 unverdicted novelty 6.0

    Empirical 2x2 factorial study on 6 statistical datasets shows format and schema constraints in LLM-based KG construction from CSV tables produce super-additive fidelity loss up to +1.180, with mismatched pairs falling...

  14. CogniFold: Always-On Proactive Memory via Cognitive Folding

    cs.AI 2026-05 unverdicted novelty 6.0

    Cognifold is a new proactive memory architecture that folds event streams into emergent cognitive structures by extending complementary learning systems theory with a prefrontal intent layer and graph topology self-or...

  15. SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory

    cs.AI 2026-05 unverdicted novelty 6.0

    SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and l...

  16. SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution

    cs.CL 2026-05 unverdicted novelty 6.0

    SkillRAE organizes skills into a graph and compiles compact, grounded contexts for LLM agents, yielding 11.7% gains on SkillsBench over prior RAE methods.

  17. Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration

    cs.CR 2026-05 unverdicted novelty 6.0

    The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.

  18. FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning

    cs.CL 2026-05 unverdicted novelty 6.0

    FT-RAG introduces a fine-grained graph-based retrieval framework for tables plus a new 9870-pair benchmark, reporting 23.5% and 59.2% gains in table- and cell-level hit rates and 62.2% higher exact-value recall over b...

  19. MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase Extraction

    cs.IR 2026-05 unverdicted novelty 6.0

    MUDY improves unsupervised keyphrase extraction by combining prompt-based scoring with candidate-aware weighting and self-attention-based multi-granular scoring to capture both local and global contextual salience, ou...

  20. Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving

    cs.CL 2026-04 unverdicted novelty 6.0

    DCM-Agent improves LLM performance on multi-paradigm optimization problems by 11-21% via dual-cluster memory construction and dynamic inference guidance.

  21. EmbodiedLGR: Integrating Lightweight Graph Representation and Retrieval for Semantic-Spatial Memory in Robotic Agents

    cs.RO 2026-04 unverdicted novelty 6.0

    A hybrid semantic graph and retrieval-augmented system with parameter-efficient VLMs achieves state-of-the-art inference and querying speeds on embodied navigation tasks with competitive accuracy.

  22. EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation

    cs.DB 2026-04 unverdicted novelty 6.0

    EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.

  23. Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs

    cs.CL 2026-04 unverdicted novelty 6.0

    Tri-RAG turns external knowledge into Condition-Proof-Conclusion triplets and retrieves via the Condition anchor to improve efficiency and quality in LLM RAG.

  24. GAM: Hierarchical Graph-based Agentic Memory for LLM Agents

    cs.AI 2026-04 unverdicted novelty 6.0

    GAM decouples event-level memory encoding from topic-level consolidation in LLM agents using hierarchical graphs to reduce interference and improve long-term coherence and retrieval.

  25. LiteSemRAG: Lightweight LLM-Free Semantic-Aware Graph Retrieval for Robust RAG

    cs.IR 2026-03 unverdicted novelty 6.0

    LiteSemRAG delivers leading MRR@10 on three benchmarks using only lightweight semantic graph methods and zero LLM tokens.

  26. Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs

    cs.IR 2026-03 unverdicted novelty 6.0

    CS-RAG is a GraphRAG framework that plans queries as ordered atomic constraints, uses anchor-relation aware retrieval, applies sufficiency checks, and falls back to text recovery to reduce drift and hallucination from...

  27. NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering

    cs.CL 2026-02 unverdicted novelty 6.0

    NeuroSymActive combines soft-unification symbolic modules, a neural path evaluator, and Monte-Carlo-style active exploration to reach strong answer accuracy on KGQA benchmarks while cutting graph lookups and model cal...

  28. HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling

    cs.AI 2026-02 unverdicted novelty 6.0

    HyMem introduces dual-granular memory storage with a lightweight summary module for fast responses and selective activation of a deep LLM module for complex queries, outperforming full-context baselines by 92.6% lower...

  29. FlexStructRAG: Flexible Structure-Aware Multi-Granular Relational Retrieval for RAG

    cs.IR 2026-02 unverdicted novelty 6.0

    FlexStructRAG jointly constructs knowledge graphs, hypergraphs, and semantic clusters with dynamic partitioning to enable query-adaptive multi-granular retrieval that improves semantic scores over standard RAG baselin...

  30. AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM

    cs.CL 2025-10 unverdicted novelty 6.0

    AtlasKV integrates billion-scale KGs into LLMs parametrically with sub-linear complexity and low memory by converting triples into key-value representations handled by the model's attention.

  31. Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation

    cs.LG 2025-10 unverdicted novelty 6.0

    A Multi-L KG and Quest-GNN with question-adaptive intra/inter-level message passing and synthesized pre-training data improves multi-hop RAG performance up to 33.8% on high-hop questions.

  32. From RAG to Memory: Non-Parametric Continual Learning for Large Language Models

    cs.CL 2025-02 unverdicted novelty 6.0

    HippoRAG 2 improves on standard RAG and prior HippoRAG by adding deeper passage integration and more effective LLM use in Personalized PageRank, delivering superior performance on factual, sense-making, and associativ...

  33. MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute Graph

    cs.CV 2026-05 unverdicted novelty 5.0

    MicroWorld constructs a multimodal attributed property graph from scientific image-caption data and augments MLLM prompts via retrieval to raise Qwen3-VL-8B performance by 37.5% on MicroVQA and 6% on MicroBench.

  34. TrajRAG: Retrieving Geometric-Semantic Experience for Zero-Shot Object Navigation

    cs.CV 2026-05 unverdicted novelty 5.0

    TrajRAG uses a topological-polar trajectory representation and hierarchical retrieval to accumulate and reuse geometric-semantic navigation experiences, improving zero-shot ObjectNav on MP3D and HM3D benchmarks.

  35. LLM-Oriented Information Retrieval: A Denoising-First Perspective

    cs.IR 2026-05 unverdicted novelty 5.0

    Denoising to maximize usable evidence density and verifiability is becoming the primary bottleneck in LLM-oriented information retrieval, conceptualized via a four-stage framework and addressed through a pipeline taxo...

  36. Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure

    cs.AI 2026-04 unverdicted novelty 5.0

    OIDA is a proposed framework that represents organizational knowledge as epistemic Knowledge Objects with class-specific importance decay and signed contradictions, plus a QUESTION mechanism that surfaces modeled igno...

  37. Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure

    cs.AI 2026-04 unverdicted novelty 5.0

    OIDA adds typed knowledge objects, decay-based importance scores, contradiction edges, and an inverse-decay QUESTION primitive for ignorance to raise epistemic fidelity beyond retrieval.

  38. CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning

    cs.CL 2026-04 unverdicted novelty 5.0

    CodaRAG improves RAG by using a CLS-inspired three-stage pipeline of knowledge consolidation, multi-dimensional associative navigation, and interference elimination, delivering 7-11% gains on GraphRAG-Bench for factua...

  39. From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning

    q-bio.QM 2026-04 unverdicted novelty 5.0

    Dual-Stream Calibration uses entropy minimization and iterative meta-learning at test time to internalize clinical evidence and outperform standard in-context learning baselines on medical tasks.

  40. RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA

    cs.CL 2025-10 unverdicted novelty 5.0

    RELOOP unifies retrieval across text, tables, and KGs via hierarchical sequences and dual-agent guided iteration, reporting EM/F1 gains over baselines on HotpotQA, HybridQA/TAT-QA, and MetaQA.

  41. MemOS: A Memory OS for AI System

    cs.CL 2025-07 unverdicted novelty 5.0

    MemOS introduces a unified memory management framework for LLMs using MemCubes to handle and evolve different memory types for improved controllability and evolvability.

  42. Retrieval-Augmented Generation with Graphs (GraphRAG)

    cs.IR 2024-12 unverdicted novelty 5.0

    A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.

  43. AssemPlanner: A Multi-Agent Based Task Planning Framework for Flexible Assembly System

    cs.RO 2026-05 unverdicted novelty 4.0

    AssemPlanner is a ReAct-based multi-agent system that autonomously generates production plans from natural language inputs by integrating scheduling, knowledge, line balancing, and scene graph feedback.

  44. LLM-Oriented Information Retrieval: A Denoising-First Perspective

    cs.IR 2026-05 unverdicted novelty 4.0

    Argues for a denoising-first paradigm in LLM-oriented information retrieval, framing challenges via a four-stage progression and providing a taxonomy of signal-to-noise optimization techniques across the pipeline.

  45. UrbanClipAtlas: A Visual Analytics Framework for Event and Scene Retrieval in Urban Videos

    cs.HC 2026-04 unverdicted novelty 4.0

    UrbanClipAtlas integrates RAG, taxonomy-aware extraction, and video grounding into a chat interface for retrieving and interpreting events in long urban videos from street intersections.

  46. Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation

    cs.CL 2026-04 unverdicted novelty 4.0

    The survey unifies LLM augmentation techniques along the single axis of structured context supplied at inference time and supplies a literature screening protocol plus deployment decision framework.

  47. Position: How can Graphs Help Large Language Models?

    cs.AI 2026-05 unverdicted novelty 3.0

    Graphs can help LLMs reduce hallucinations, boost reasoning via prompting techniques, and better process structured data.

Reference graph

Works this paper leans on

48 extracted references · 48 canonical work pages · cited by 44 Pith papers · 5 internal anchors

  1. [2]

    In search of needles in a 10m haystack: Recurrent memory finds what llms miss,

    In search of needles in a 10m haystack: Recurrent memory finds what llms miss , author=. arXiv preprint arXiv:2402.10790 , year=

    work page arXiv

  2. [3]

    Transactions of the Association for Computational Linguistics , volume=

    Lost in the middle: How language models use long contexts , author=. Transactions of the Association for Computational Linguistics , volume=. 2024 , publisher=

    work page 2024

  3. [4]

    HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

    HotpotQA: A dataset for diverse, explainable multi-hop question answering , author=. arXiv preprint arXiv:1809.09600 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  4. [5]

    International Conference on Learning Representations (ICLR) , year=

    One For All: Towards Training One Graph Model For All Classification Tasks , author=. International Conference on Learning Representations (ICLR) , year=

    work page

  5. [6]

    Advances in Information Retrieval: 31th European Conference on IR Research, ECIR 2009, Toulouse, France, April 6-9, 2009

    Classifying and characterizing query intent , author=. Advances in Information Retrieval: 31th European Conference on IR Research, ECIR 2009, Toulouse, France, April 6-9, 2009. Proceedings 31 , pages=. 2009 , organization=

    work page 2009

  6. [7]

    Information Processing & Management , volume=

    Determining the informational, navigational, and transactional intent of Web queries , author=. Information Processing & Management , volume=. 2008 , publisher=

    work page 2008

  7. [8]

    Transactions of the Association for Computational Linguistics (TACL) , volume=

    In-context retrieval-augmented language models , author=. Transactions of the Association for Computational Linguistics (TACL) , volume=. 2023 , publisher=

    work page 2023

  8. [9]

    International Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=

    GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs , author=. International Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=

    work page

  9. [13]

    A Survey of Large Language Models

    A survey of large language models , author=. arXiv preprint arXiv:2303.18223 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  10. [14]

    International Conference on Knowledge Discovery and Data Mining (KDD) , pages=

    A survey on rag meeting llms: Towards retrieval-augmented large language models , author=. International Conference on Knowledge Discovery and Data Mining (KDD) , pages=

    work page

  11. [15]

    G-retriever: Retrieval-augmented generation for textual graph understanding and question answering,

    G-retriever: Retrieval-augmented generation for textual graph understanding and question answering , author=. arXiv preprint arXiv:2402.07630 , year=

    work page arXiv

  12. [16]

    Knowledge-augmented language model prompting for zero-shot knowledge graph question answering, 2023

    Knowledge-augmented language model prompting for zero-shot knowledge graph question answering , author=. arXiv preprint arXiv:2306.04136 , year=

    work page arXiv

  13. [17]

    ACM International Conference on Research and Development in Information Retrieval (SIGIR) , pages=

    Graphgpt: Graph instruction tuning for large language models , author=. ACM International Conference on Research and Development in Information Retrieval (SIGIR) , pages=

    work page

  14. [18]

    International Conference on Machine Learning (ICML) , year=

    LLaGA: Large Language and Graph Assistant , author=. International Conference on Machine Learning (ICML) , year=

    work page

  15. [19]

    ACM International Conference on Research and Development in Information Retrieval (SIGIR) , pages=

    RAG-Ex: A Generic Framework for Explaining Retrieval Augmented Generation , author=. ACM International Conference on Research and Development in Information Retrieval (SIGIR) , pages=

    work page

  16. [20]

    International Conference of the European Chapter of the Association for Computational Linguistics (EACL) , pages=

    RAGAs: Automated Evaluation of Retrieval Augmented Generation , author=. International Conference of the European Chapter of the Association for Computational Linguistics (EACL) , pages=

    work page

  17. [21]

    ACM International Conference on Research and Development in Information Retrieval (SIGIR) , pages=

    Evaluating retrieval quality in retrieval-augmented generation , author=. ACM International Conference on Research and Development in Information Retrieval (SIGIR) , pages=

    work page

  18. [22]

    International Conference on Knowledge Discovery and Data Mining (KDD) , pages=

    R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models , author=. International Conference on Knowledge Discovery and Data Mining (KDD) , pages=

    work page

  19. [24]

    International Conference on Neural Information Processing Systems (NeurIPS) , volume=

    Recipe for a general, powerful, scalable graph transformer , author=. International Conference on Neural Information Processing Systems (NeurIPS) , volume=

    work page

  20. [25]

    ICML , pages=

    How powerful are spectral graph neural networks , author=. ICML , pages=. 2022 , organization=

    work page 2022

  21. [27]

    International Conference on Knowledge Discovery and Data Mining (KDD) , pages=

    Graph-aware language model pre-training on a large graph corpus can help multiple graph applications , author=. International Conference on Knowledge Discovery and Data Mining (KDD) , pages=

    work page

  22. [28]

    arXiv preprint arXiv:2402.15183 , year=

    Graphedit: Large language models for graph structure learning , author=. arXiv preprint arXiv:2402.15183 , year=

    work page arXiv

  23. [29]

    Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , pages=

    Higpt: Heterogeneous graph language model , author=. Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining , pages=

    work page

  24. [30]

    Harnessing explanations: Llm-to-lm interpreter for enhanced text- attributed graph representation learning.arXiv preprint arXiv:2305.19523, 2023

    Explanations as Features: LLM-Based Features for Text-Attributed Graphs , author=. arXiv preprint arXiv:2305.19523 , year=

    work page arXiv

  25. [31]

    arXiv preprint arXiv:2403.01121 , year=

    Opengraph: Towards open graph foundation models , author=. arXiv preprint arXiv:2403.01121 , year=

    work page arXiv

  26. [32]

    arXiv preprint arXiv:2310.09872 , year=

    Empower text-attributed graphs learning with large language models (llms) , author=. arXiv preprint arXiv:2310.09872 , year=

    work page arXiv

  27. [33]

    2024 , eprint=

    MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery , author=. 2024 , eprint=

    work page 2024

  28. [36]

    Congrat: Self-supervised contrastive pretraining for joint graph and text embeddings

    William Brannon, Suyash Fulay, Hang Jiang, Wonjune Kang, Brandon Roy, Jad Kabbara, and Deb Roy. Congrat: Self-supervised contrastive pretraining for joint graph and text embeddings. arXiv preprint arXiv:2305.14321, 2023

    work page arXiv 2023

  29. [37]

    Rq-rag: Learning to refine queries for retrieval augmented generation.arXiv preprint arXiv:2404.00610,

    Chi-Min Chan, Chunpu Xu, Ruibin Yuan, Hongyin Luo, Wei Xue, Yike Guo, and Jie Fu. Rq-rag: Learning to refine queries for retrieval augmented generation. arXiv preprint arXiv:2404.00610, 2024

    work page arXiv 2024

  30. [38]

    Llaga: Large language and graph assistant

    Runjin Chen, Tong Zhao, AJAY KUMAR JAISWAL, Neil Shah, and Zhangyang Wang. Llaga: Large language and graph assistant. In International Conference on Machine Learning (ICML), 2024

    work page 2024

  31. [39]

    From Local to Global: A Graph RAG Approach to Query-Focused Summarization

    Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  32. [40]

    Ragas: Automated evaluation of retrieval augmented generation

    Shahul Es, Jithin James, Luis Espinosa Anke, and Steven Schockaert. Ragas: Automated evaluation of retrieval augmented generation. In International Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp.\ 150--158, 2024

    work page 2024

  33. [41]

    A survey on rag meeting llms: Towards retrieval-augmented large language models

    Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. A survey on rag meeting llms: Towards retrieval-augmented large language models. In International Conference on Knowledge Discovery and Data Mining (KDD), pp.\ 6491--6501, 2024

    work page 2024

  34. [42]

    Precise zero-shot dense retrieval without relevance labels,

    Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. Precise zero-shot dense retrieval without relevance labels. arXiv preprint arXiv:2212.10496, 2022

    work page arXiv 2022

  35. [43]

    Retrieval-Augmented Generation for Large Language Models: A Survey

    Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  36. [44]

    Grenade: Graph-centric language model for self-supervised representation learning on text-attributed graphs

    Yichuan Li, Kaize Ding, and Kyumin Lee. Grenade: Graph-centric language model for self-supervised representation learning on text-attributed graphs. In International Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.\ 2745--2757, 2023

    work page 2023

  37. [45]

    One for all: Towards training one graph model for all classification tasks

    Hao Liu, Jiarui Feng, Lecheng Kong, Ningyue Liang, Dacheng Tao, Yixin Chen, and Muhan Zhang. One for all: Towards training one graph model for all classification tasks. In International Conference on Learning Representations (ICLR), 2024

    work page 2024

  38. [46]

    Crud-rag: A comprehensive chinese benchmark for retrieval-augmented generation of large language models,

    Yuanjie Lyu, Zhiyu Li, Simin Niu, Feiyu Xiong, Bo Tang, Wenjin Wang, Hao Wu, Huanyong Liu, Tong Xu, and Enhong Chen. Crud-rag: A comprehensive chinese benchmark for retrieval-augmented generation of large language models. arXiv preprint arXiv:2401.17043, 2024

    work page arXiv 2024

  39. [47]

    arXiv preprint arXiv:2409.05591 (2024)

    Hongjin Qian, Peitian Zhang, Zheng Liu, Kelong Mao, and Zhicheng Dou. Memorag: Moving towards next-gen rag via memory-inspired knowledge discovery, 2024. URL https://arxiv.org/abs/2409.05591

    work page arXiv 2024

  40. [48]

    In-context retrieval-augmented language models

    Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics (TACL), 11: 0 1316--1331, 2023

    work page 2023

  41. [49]

    Recipe for a general, powerful, scalable graph transformer

    Ladislav Ramp \'a s ek, Michael Galkin, Vijay Prakash Dwivedi, Anh Tuan Luu, Guy Wolf, and Dominique Beaini. Recipe for a general, powerful, scalable graph transformer. International Conference on Neural Information Processing Systems (NeurIPS), 35: 0 14501--14515, 2022

    work page 2022

  42. [50]

    Evaluating retrieval quality in retrieval-augmented generation

    Alireza Salemi and Hamed Zamani. Evaluating retrieval quality in retrieval-augmented generation. In ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp.\ 2395--2400, 2024

    work page 2024

  43. [51]

    Rag-ex: A generic framework for explaining retrieval augmented generation

    Viju Sudhi, Sinchana Ramakanth Bhat, Max Rudat, and Roman Teucher. Rag-ex: A generic framework for explaining retrieval augmented generation. In ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp.\ 2776--2780, 2024

    work page 2024

  44. [52]

    Graphgpt: Graph instruction tuning for large language models

    Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, and Chao Huang. Graphgpt: Graph instruction tuning for large language models. In ACM International Conference on Research and Development in Information Retrieval (SIGIR), pp.\ 491--500, 2024

    work page 2024

  45. [53]

    R-eval: A unified toolkit for evaluating domain knowledge of retrieval augmented large language models

    Shangqing Tu, Yuanchun Wang, Jifan Yu, Yuyang Xie, Yaran Shi, Xiaozhi Wang, Jing Zhang, Lei Hou, and Juanzi Li. R-eval: A unified toolkit for evaluating domain knowledge of retrieval augmented large language models. In International Conference on Knowledge Discovery and Data Mining (KDD), pp.\ 5813--5824, 2024

    work page 2024

  46. [54]

    Graph-aware language model pre-training on a large graph corpus can help multiple graph applications

    Han Xie, Da Zheng, Jun Ma, Houyu Zhang, Vassilis N Ioannidis, Xiang Song, Qing Ping, Sheng Wang, Carl Yang, Yi Xu, et al. Graph-aware language model pre-training on a large graph corpus can help multiple graph applications. In International Conference on Knowledge Discovery and Data Mining (KDD), pp.\ 5270--5281, 2023

    work page 2023

  47. [55]

    RankRAG: Unifying context ranking with retrieval-augmented generation in LLMs.arXiv preprint arXiv:2407.02485, 2024

    Yue Yu, Wei Ping, Zihan Liu, Boxin Wang, Jiaxuan You, Chao Zhang, Mohammad Shoeybi, and Bryan Catanzaro. Rankrag: Unifying context ranking with retrieval-augmented generation in llms. arXiv preprint arXiv:2407.02485, 2024

    work page arXiv 2024

  48. [56]

    Retrieval-Augmented Generation for AI-Generated Content: A Survey

    Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, and Bin Cui. Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473, 2024

    work page internal anchor Pith review arXiv 2024