Pith. sign in

REVIEW 7 cited by

Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation

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 2407.10805 v7 pith:CPCDD6YK submitted 2024-07-15 cs.CL cs.AI

Shengjie Ma , Chengjin Xu , Xuhui Jiang , Muzhi Li , Huaren Qu , Cehao Yang , Jiaxin Mao , Jian Guo This is my paper
classification cs.CLcs.AI
keywords retrievaltog-2knowledgecontextgraphllmsreasoningcontexts
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-augmented generation (RAG) has improved large language models (LLMs) by using knowledge retrieval to overcome knowledge deficiencies. However, current RAG methods often fall short of ensuring the depth and completeness of retrieved information, which is necessary for complex reasoning tasks. In this work, we introduce Think-on-Graph 2.0 (ToG-2), a hybrid RAG framework that iteratively retrieves information from both unstructured and structured knowledge sources in a tight-coupling manner. Specifically, ToG-2 leverages knowledge graphs (KGs) to link documents via entities, facilitating deep and knowledge-guided context retrieval. Simultaneously, it utilizes documents as entity contexts to achieve precise and efficient graph retrieval. ToG-2 alternates between graph retrieval and context retrieval to search for in-depth clues relevant to the question, enabling LLMs to generate answers. We conduct a series of well-designed experiments to highlight the following advantages of ToG-2: 1) ToG-2 tightly couples the processes of context retrieval and graph retrieval, deepening context retrieval via the KG while enabling reliable graph retrieval based on contexts; 2) it achieves deep and faithful reasoning in LLMs through an iterative knowledge retrieval process of collaboration between contexts and the KG; and 3) ToG-2 is training-free and plug-and-play compatible with various LLMs. Extensive experiments demonstrate that ToG-2 achieves overall state-of-the-art (SOTA) performance on 6 out of 7 knowledge-intensive datasets with GPT-3.5, and can elevate the performance of smaller models (e.g., LLAMA-2-13B) to the level of GPT-3.5's direct reasoning. The source code is available on https://github.com/IDEA-FinAI/ToG-2.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 9 citations worldwide. Full citation record

  1. Harness-G: A Graph-Structured Harness for Search Agents

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Restricting RL search agents to selecting evidence sentences and entity lookups from a graph-structured menu, with structured non-myopic credit, improves multi-hop QA F1 by up to 10.7 points over Graph-R1.

  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. XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation

    cs.IR 2025-06 conditional novelty 6.0 of 10

    A visual analytics framework helps GraphRAG developers trace suspicious retrievals through graph construction and LLM invocation stages, with a user study suggesting faster, more accurate failure diagnosis than an exi...

  4. Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks

    cs.IR 2025-05 conditional novelty 5.0 of 10

    Offline walks over a knowledge graph, verbalized into text and retrieved by embedding similarity, let a single LLM call answer multi-hop questions competitively without any fine-tuning.

  5. LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking

    cs.IR 2025-06 conditional novelty 4.0 of 10

    A KG-enhanced LlamaRec that feeds user-specific relation paths into a Llama-2 ranker reports modest MRR, NDCG, and Recall gains on two benchmarks.

  6. DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation

    cs.CL 2025-06 reject novelty 4.0 of 10

    A small model prompted with evidence and knowledge graphs generated by GPT-4o scores much higher on QA benchmarks, but the result is not true distillation and may be contaminated by teacher answer leakage.

  7. From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies

    cs.CL 2025-06 conditional novelty 3.0 of 10

    A review that organizes the knowledge graph and large language model integration field into three categories and argues for more attention to scalability, efficiency, and data quality.

Pith tools