REVIEW 18 cited by
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
Not yet reviewed by Pith; the record is open.
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
abstract
Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially in scenarios requiring deep and responsible reasoning. These issues could be partially addressed by introducing external knowledge graphs (KG) in LLM reasoning. In this paper, we propose a new LLM-KG integrating paradigm ``$\hbox{LLM}\otimes\hbox{KG}$'' which treats the LLM as an agent to interactively explore related entities and relations on KGs and perform reasoning based on the retrieved knowledge. We further implement this paradigm by introducing a new approach called Think-on-Graph (ToG), in which the LLM agent iteratively executes beam search on KG, discovers the most promising reasoning paths, and returns the most likely reasoning results. We use a number of well-designed experiments to examine and illustrate the following advantages of ToG: 1) compared with LLMs, ToG has better deep reasoning power; 2) ToG has the ability of knowledge traceability and knowledge correctability by leveraging LLMs reasoning and expert feedback; 3) ToG provides a flexible plug-and-play framework for different LLMs, KGs and prompting strategies without any additional training cost; 4) the performance of ToG with small LLM models could exceed large LLM such as GPT-4 in certain scenarios and this reduces the cost of LLM deployment and application. As a training-free method with lower computational cost and better generality, ToG achieves overall SOTA in 6 out of 9 datasets where most previous SOTAs rely on additional training.
Forward citations
Cited by 18 Pith papers
-
KAMR: Grounding Generation via Knowledge-Aligned Multi-hop Retrieval
Partial-alignment contrastive pretraining plus anchor-then-expand graph retrieval improves multi-hop KG evidence recovery and downstream QA over strong dense and graph RAG baselines.
-
Co-Evolving Graph and Text Memory for Training-Free Multi-Hop Question Answering
Bidirectional graph↔text memory synchronization with active retraction of stale claims improves training-free multi-hop QA on 2Wiki, MuSiQue, Bamboogle, HotpotQA, WebQSP, and CWQ.
-
When Thinking Before Retrieval Hurts: TraceBound Diagnostics for Adaptive Knowledge-Graph Retrieval
Profile and trace conditioning on an ARK-style retriever improves inspectability but consistently degrades Hit@5, Recall@20, and MRR on STaRK with open-weight Qwen3 controllers.
-
Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction
A four-stage LLM framework that constructs, audits, and aggregates explicit causal chains outperforms prompting baselines on three context-free causal QA benchmarks.
-
NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering
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...
-
KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering
KG-ViP fuses scene graphs and commonsense graphs via a query-based retrieval-and-fusion pipeline to improve multi-modal LLM performance on visual question answering.
-
Ella: Embodied Social Agents with Lifelong Memory
Ella, an embodied social agent with a name-centric semantic memory and a spatiotemporal episodic memory, outperformed two re-implemented baselines in social influence and leadership tasks in a 3D simulation.
-
Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation
ReG refines weak graph-retriever supervision with LLM-selected reasoning chains and reorganizes retrieved triples into coherent evidence chains, improving KGQA accuracy, data efficiency, and reasoning token efficiency.
-
XGraphRAG: Interactive Visual Analysis for Graph-based Retrieval-Augmented Generation
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...
-
KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
KBQA-R1 achieves state-of-the-art KBQA results by combining GRPO reinforcement learning with an action-based multi-turn agent and reference-conditioned warm-start data.
-
Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs
An LLM that iteratively inspects 1-hop neighbors of a knowledge-graph entity and chooses the next relation achieves state-of-the-art KGQA scores on six Freebase/Wikidata benchmarks without fine-tuning.
-
KnowCoder-V2: Deep Knowledge Analysis
KnowCoder-V2 augments deep research with offline knowledge organization and code-based knowledge computation, reporting gains on information extraction, KBQA, and LLM-judged report generation.
-
KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language Models
KERL uses a food knowledge graph and three LoRA adapters on one LLM to recommend constrained recipes, generate cooking instructions, and produce micro-nutrition details.
-
DTKG: Dual-Track Knowledge Graph-Verified Reasoning Framework for Multi-Hop QA
DTKG routes multi-hop questions into either a fact-verification or knowledge-graph chain-reasoning branch, reporting modest accuracy gains on four QA benchmarks.
-
REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing
A category-routed hybrid of RAG and knowledge-graph retrieval answers Vietnamese university-regulation questions with F1 98.89% on the authors' own dataset — about 0.2 points above plain RAG.
-
Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
In a small comparative study, GraphRAG outscored spaCy and CoreNLP-based KG-QA pipelines on reasoning-heavy questions, but the evaluation design conflates method choice with pipeline architecture.
-
Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE
KG-SMILE applies perturbation and linear regression to a knowledge graph to attribute which entities and relations drive a GraphRAG system's answers.
-
Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering
SRP combines reference retrieval, relation checking, and iterative self-reflection to improve LLM question answering over knowledge graphs, reporting gains over Readi on WebQSP, CWQ, and GrailQA.
Discussion (0). Continue with ORCID to comment.