Lune

ACL Findings2025

ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLM

Hoang Pham, Thanh-Do Nguyen, Khac-Hoai Nam Bui

Abstract

Integrating knowledge graphs (KGs) to enhance the reasoning capabilities of large language models (LLMs) is an emerging research challenge in claim verification. While KGs provide structured, semantically rich representations well-suited for reasoning, most existing verification methods rely on unstructured text corpora, limiting their ability to effectively leverage KGs. Additionally, despite possessing strong reasoning abilities, modern LLMs struggle with multi-step modular pipelines and reasoning over KGs without adaptation. To address these challenges, we propose ClaimPKG 1 , an end-to-end framework that seamlessly integrates LLM reasoning with structured knowledge from KGs. Specifically, the main idea of ClaimPKG is to employ a lightweight, specialized LLM to represent the input claim as pseudo-subgraphs, guiding a dedicated subgraph retrieval module to identify relevant KG subgraphs. These retrieved subgraphs are then processed by a general-purpose LLM to produce the final verdict and justification. Extensive experiments on the FactKG dataset demonstrate that ClaimPKG achieves state-of-theart performance, outperforming strong baselines in this research field by 9%-12% accuracy points across multiple categories. Furthermore, ClaimPKG exhibits zero-shot generalizability to unstructured datasets such as HoVer and FEVEROUS, effectively combining structured knowledge from KGs with LLM reasoning across various LLM backbones.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

3 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Self-Consistency Improves Chain of Thought Reasoning in Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
  • Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning cites Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
  • Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking cites Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
  • Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
  • Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Extending First-Order Logic for Factual Reasoning over Knowledge Graphs cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning cites Self-Consistency Improves Chain of Thought Reasoning in Language Models
  • Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval cites Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
  • KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval cites Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers3

  1. Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-CheckingShuzhi Gong, Richard O. Sinnott, Jianzhong Qi, Cécile Paris et al.SIGIR 2026 · 2 citations
  2. KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query RetrievalChi Minh Bui, Ngoc Mai Thieu, Van Vinh Nguyen, Jason J. Jung et al.EMNLP 2025 · 1 citation
  3. Extending First-Order Logic for Factual Reasoning over Knowledge GraphsYuanzhen Hao, Desheng WuACL 2026

Builds on16

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
  3. Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
  4. Reasoning on Graphs: Faithful and Interpretable Large Language Model ReasoningLinhao Luo, Yuan-Fang Li, Gholamreza Haffari, Shirui PanICLR 2024 · 499 citations
  5. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge GraphJiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang et al.ICLR 2024 · 247 citations

Related papers

  1. Fact Verification on Knowledge Graph via Programmatic Graph ReasoningYuanzhen Hao, Desheng WuEMNLP Findings 2025
  2. KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language ModelsJiho Kim, Yeonsu Kwon, Yohan Jo, Edward ChoiEMNLP Findings 2023 · 47 citations
  3. Reflection on Knowledge Graph for Large Language Models ReasoningYigeng Zhou, Wu Li, Yifan Lu, Jing Li et al.ACL Findings 2025 · 8 citations
  4. LightPROF: A Lightweight Reasoning Framework for Large Language Model on Knowledge GraphTu Ao, Yanhua Yu, Yuling Wang, Yang Deng et al.AAAI 2025 · 28 citations
  5. ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge GraphsMinbae Park, Hyemin Yang, Jeonghyun Kim, Kunsoo Park et al.AAAI 2026
Dusk over the sea between two cliffs drawn in fine vertical lines