Pith. sign in

REVIEW 8 cited by

Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs

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

arxiv 2404.07103 v3 pith:4HGYUKIB submitted 2024-04-10 cs.CL cs.IRcs.LG

classification cs.CLcs.IRcs.LG
keywords graphgraphsllmsgraph-cotknowledgereasoningaugmentaugmenting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs), while exhibiting exceptional performance, suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora to alleviate the issue. However, in many domains, texts are interconnected (e.g., academic papers in a bibliographic graph are linked by citations and co-authorships) which form a (text-attributed) graph. The knowledge in such graphs is encoded not only in single texts/nodes but also in their associated connections. To facilitate the research of augmenting LLMs with graphs, we manually construct a Graph Reasoning Benchmark dataset called GRBench, containing 1,740 questions that can be answered with the knowledge from 10 domain graphs. Then, we propose a simple and effective framework called Graph Chain-of-thought (Graph-CoT) to augment LLMs with graphs by encouraging LLMs to reason on the graph iteratively. Each Graph-CoT iteration consists of three sub-steps: LLM reasoning, LLM-graph interaction, and graph execution. We conduct systematic experiments with three LLM backbones on GRBench, where Graph-CoT outperforms the baselines consistently. The code is available at https://github.com/PeterGriffinJin/Graph-CoT.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. GraphRunner: A Multi-Stage Framework for Efficient and Accurate Graph-Based Retrieval

    cs.IR 2025-07 conditional novelty 6.0 of 10

    GraphRunner improves graph-based retrieval by generating and validating a complete traversal plan before executing high-level multi-hop actions, outperforming Graph-CoT on GRBENCH with 10 to 50 percent higher accuracy...

  2. ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A verifiable RL proxy task that asks VLMs to locate a single injected hallucination in a 200-word caption improves visual perception and transfers to math and abstract reasoning benchmarks.

  3. Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering

    cs.CL 2025-06 conditional novelty 6.0 of 10

    RAPL combines LLM-rationalized path labels, line graph transformation, and path-based decoding to improve graph retrieval for KGQA, reporting state-of-the-art results on WebQSP and CWQ.

  4. How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A new GraphRAG evaluation framework using graph-grounded questions and bias-correction yields much smaller win rates than earlier reports, casting doubt on reported GraphRAG gains.

  5. What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering

    cs.AI 2026-07 conditional novelty 5.0 of 10

    The paper defines prompt graph engineering via four necessary and sufficient conditions (explicit structure, structure/content separation, executable semantics, first-class artifact) and an inclusion/exclusion test th...

  6. Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models

    cs.AI 2025-05 conditional novelty 5.0 of 10

    DTO constructs compressed, ground-truth-curated reasoning trajectories from LRM outputs and uses them as preferred responses in SimPO, yielding up to 12% accuracy gains and roughly 40% token reduction on math benchmarks.

  7. 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.

  8. Multilevel Analysis of Cryptocurrency News using RAG Approach with Fine-Tuned Mistral Large Language Model

    cs.CL 2025-08 reject novelty 3.0 of 10

    A fine-tuned Mistral 7B model produces graph and text summaries, sentiment scores, and stacked meta-summaries of crypto news, but the paper reports no quantitative evaluation.

Pith tools