arxiv: 2604.06666 · v1 · submitted 2026-04-08 · 💻 cs.CL · cs.AI

Recognition: no theorem link

A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM

Bo Wang , Jing Ma , Hongzhan Lin , Zhiwei Yang , Ruichao Yang , Yuan Tian , Yi Chang

Authors on Pith no claims yet

Pith reviewed 2026-05-10 17:54 UTC · model grok-4.3

classification 💻 cs.CL cs.AI

keywords explainable fake news detectionlarge language modelsretrieval-augmented generationgraph neural networksclaim decomposition

0 comments

The pith

Decomposing news claims into sub-claims in a dependency graph enables reliable fake news detection and explanations from unverified reports.

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

The paper proposes a framework called G-Defense that breaks a news claim into multiple sub-claims and links them through dependency relationships in a graph. For each sub-claim, it retrieves evidence from external sources using retrieval-augmented generation and creates competing explanations to evaluate consistency. A specialized inference module then processes the graph to determine the overall truthfulness of the claim. This method also prompts a large language model to produce an intuitive graph showing the explanations. The goal is to offer detailed, human-friendly explanations for every part of the claim while handling the challenge of unverified information in breaking news stories.

Core claim

By constructing a claim-centered graph through sub-claim decomposition and dependency modeling, generating competing explanations via RAG for each sub-claim, and applying a defense-like graph-based inference, the framework achieves state-of-the-art performance in veracity detection and explanation quality using only unverified reports.

What carries the argument

The claim-centered graph, which decomposes the claim into sub-claims and models their dependency relationships to support veracity assessment and explanation generation.

If this is right

G-Defense provides fine-grained explanations based solely on unverified reports.
It achieves state-of-the-art performance in veracity detection.
The approach generates an intuitive explanation graph to assist public verification.
It addresses inefficiency in existing methods for breaking news.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

This structure could potentially be adapted for verifying claims in scientific literature or legal documents.
Future work might test the framework on multilingual claims or in low-resource settings.
Integrating user feedback into the graph could improve explanation relevance over time.

Load-bearing premise

That modeling sub-claim dependencies in a graph along with competing explanations from unverified reports will lead to accurate overall veracity judgments.

What would settle it

Testing the system on a set of news claims where the retrieved reports contain deliberate misinformation and checking whether the accuracy of veracity predictions falls below current baselines.

Figures

Figures reproduced from arXiv: 2604.06666 by Bo Wang, Hongzhan Lin, Jing Ma, Ruichao Yang, Yi Chang, Yuan Tian, Zhiwei Yang.

**Figure 2.** Figure 2: An architecture overview of the proposed [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗

**Figure 3.** Figure 3: An illustrative example of the graph construction process. [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗

**Figure 4.** Figure 4: An illustrative example of the competing explanation generation process for a sub-claim. [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗

**Figure 5.** Figure 5: Distribution of claims by the number of decomposed sub-claims in the test sets of RAWFC and [PITH_FULL_IMAGE:figures/full_fig_p017_5.png] view at source ↗

**Figure 6.** Figure 6: MacF1 scores of G-Defense and its w/o-sub-claims variant grouped by the number of sub-claims on [PITH_FULL_IMAGE:figures/full_fig_p020_6.png] view at source ↗

**Figure 7.** Figure 7: Explanation evaluation results using a 5-Point Likert scale rating by five human annotators on 30 [PITH_FULL_IMAGE:figures/full_fig_p022_7.png] view at source ↗

**Figure 8.** Figure 8: Confusion matrices of judgment results from five annotators on 30 randomly sampled claims. The [PITH_FULL_IMAGE:figures/full_fig_p023_8.png] view at source ↗

read the original abstract

Explainable fake news detection aims to assess the veracity of news claims while providing human-friendly explanations. Existing methods incorporating investigative journalism are often inefficient and struggle with breaking news. Recent advances in large language models (LLMs) enable leveraging externally retrieved reports as evidence for detection and explanation generation, but unverified reports may introduce inaccuracies. Moreover, effective explainable fake news detection should provide a comprehensible explanation for all aspects of a claim to assist the public in verifying its accuracy. To address these challenges, we propose a graph-enhanced defense framework (G-Defense) that provides fine-grained explanations based solely on unverified reports. Specifically, we construct a claim-centered graph by decomposing the news claim into several sub-claims and modeling their dependency relationships. For each sub-claim, we use the retrieval-augmented generation (RAG) technique to retrieve salient evidence and generate competing explanations. We then introduce a defense-like inference module based on the graph to assess the overall veracity. Finally, we prompt an LLM to generate an intuitive explanation graph. Experimental results demonstrate that G-Defense achieves state-of-the-art performance in both veracity detection and the quality of its explanations.

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.

Desk Editor's Note private letter to a colleague

G-Defense combines claim graphs, RAG competing explanations, and graph inference for explainable fake news detection, but the abstract leaves the key filtering of bad evidence underspecified.

read the letter

The paper's core move is to decompose a news claim into sub-claims, build a dependency graph around them, pull competing explanations via RAG for each one, run a defense-style inference pass on that graph, and finally prompt an LLM for an intuitive explanation graph. That pipeline is presented as new, and the framing does address the real issue that unverified retrieved reports can inject errors into LLM-based detection. The authors correctly note that existing methods either rely on slow human-style investigation or risk propagating inaccuracies from raw RAG output, and the sub-claim decomposition plus competing-explanation step is a reasonable way to aim for finer-grained, more comprehensive explanations than single-shot LLM verdicts. The graph structure itself is a straightforward way to capture dependencies that a flat prompt would miss. On the positive side, the work stays grounded in the practical constraints of breaking news, where fresh reports are often unverified, and it tries to turn that constraint into a feature by generating explicit alternatives rather than hiding them. The stress-test concern about missing reliability weighting holds up on the abstract: the description says the inference module assesses overall veracity but gives no concrete mechanism—attention weights, consistency scoring, or otherwise—for down-weighting a misleading report before it affects the final label. If the graph simply passes all signals forward, the defense claim weakens. No equations, ablation details, or error analysis appear in the provided text, so the SOTA assertion on both detection accuracy and explanation quality cannot be checked yet. This paper is aimed at NLP researchers working on misinformation tools who already use RAG and LLMs and want a graph layer on top. A reader looking for a concrete system sketch rather than a theoretical advance would find usable ideas here. I would send it to peer review; the integration is coherent enough and the problem is important enough that referees can usefully pressure the authors on the inference details and the experimental controls.

Referee Report

2 major / 2 minor

Summary. The manuscript proposes G-Defense, a graph-enhanced framework for explainable fake news detection. It decomposes a news claim into sub-claims, builds a claim-centered graph capturing dependency relations, applies RAG to retrieve salient evidence and generate competing explanations per sub-claim from unverified reports, runs a defense-like inference module over the graph to produce an overall veracity label, and finally prompts an LLM to output an intuitive explanation graph. The authors claim that this yields state-of-the-art performance on both veracity detection and explanation quality.

Significance. If the experimental claims hold and the inference module demonstrably filters unreliable signals, the work would offer a concrete advance in handling unverified external evidence for explainable detection. The combination of sub-claim decomposition, competing explanations, and graph-structured aggregation addresses a recognized limitation of direct LLM prompting on breaking news; reproducible code or parameter-free derivations would further strengthen its impact.

major comments (2)

[§3] §3 (Method), inference module description: the central claim that the framework produces reliable veracity judgments from unverified RAG reports rests on the defense-like inference module, yet no equations, attention mechanism, aggregation rule, or pseudocode are supplied for how the module weights, filters, or detects inconsistencies among competing explanations. Without an explicit reliability signal or down-weighting step, error propagation from any single misleading report cannot be ruled out.
[Experimental section] Experimental section (tables/figures reporting results): the SOTA claim is asserted but the manuscript provides no quantitative metrics (accuracy, F1, explanation quality scores), baseline comparisons, ablation results isolating the graph or inference components, or error analysis on cases where RAG reports conflict. This prevents verification that the proposed defense mechanism, rather than the underlying LLM or retrieval, drives the reported gains.

minor comments (2)

[§3.1] Notation for the claim-centered graph (nodes, edges, sub-claim dependencies) is introduced without a formal definition or diagram legend, making it difficult to follow how dependency relations are encoded.
The prompt templates used for RAG evidence retrieval and final explanation-graph generation are not provided in the appendix or main text, hindering reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We are grateful to the referee for the insightful comments that will help enhance the clarity and completeness of our manuscript. We address each major comment below and commit to making the necessary revisions.

read point-by-point responses

Referee: [§3] §3 (Method), inference module description: the central claim that the framework produces reliable veracity judgments from unverified RAG reports rests on the defense-like inference module, yet no equations, attention mechanism, aggregation rule, or pseudocode are supplied for how the module weights, filters, or detects inconsistencies among competing explanations. Without an explicit reliability signal or down-weighting step, error propagation from any single misleading report cannot be ruled out.

Authors: We thank the referee for highlighting the need for a more formal description of the inference module. While Section 3 describes the defense-like inference as performing graph-based propagation to assess veracity by considering dependencies and competing explanations, we agree that explicit mathematical formulations are missing. In the revised version, we will add equations detailing the aggregation rule, including a consistency-based weighting mechanism that down-weights inconsistent explanations, along with pseudocode for the module. This will better illustrate how the framework mitigates error propagation from unverified reports. revision: yes
Referee: [Experimental section] Experimental section (tables/figures reporting results): the SOTA claim is asserted but the manuscript provides no quantitative metrics (accuracy, F1, explanation quality scores), baseline comparisons, ablation results isolating the graph or inference components, or error analysis on cases where RAG reports conflict. This prevents verification that the proposed defense mechanism, rather than the underlying LLM or retrieval, drives the reported gains.

Authors: We appreciate the referee's concern regarding the experimental validation. The current manuscript includes experimental results demonstrating SOTA performance, but we acknowledge that the presentation could be improved with more comprehensive details. We will revise the experimental section to include explicit quantitative metrics such as accuracy and F1 scores, detailed baseline comparisons, ablation studies isolating the contributions of the graph structure and inference module, and an error analysis on cases involving conflicting RAG reports. This will provide stronger evidence that the defense mechanism drives the improvements. revision: yes

Circularity Check

0 steps flagged

No significant circularity; framework composes standard components

full rationale

The paper describes a G-Defense framework that decomposes claims into sub-claims for graph construction, applies RAG to retrieve evidence and generate competing explanations per sub-claim, uses a graph-based inference module for veracity assessment, and prompts an LLM for final explanations. No equations, mathematical derivations, fitted parameters renamed as predictions, or load-bearing self-citations appear in the abstract or described structure. The central claims rest on composing existing techniques (graph modeling, RAG, LLM prompting) rather than reducing to self-referential inputs or prior author results by construction. Experimental SOTA claims are presented as empirical outcomes without internal circular reduction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only view supplies no explicit free parameters, axioms, or invented entities; the approach rests on standard, previously published techniques of graph construction, retrieval-augmented generation, and LLM prompting.

pith-pipeline@v0.9.0 · 5518 in / 1163 out tokens · 41828 ms · 2026-05-10T17:54:40.883114+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

88 extracted references · 56 canonical work pages · 12 internal anchors

[1]

Tariq Alhindi, Savvas Petridis, and Smaranda Muresan. 2018. Where is your evidence: Improving fact-checking by justification modeling. In Proceedings of the first workshop on fact extraction and verification (FEVER). 85–90

2018
[2]

Jennifer Allen, Antonio A Arechar, Gordon Pennycook, and David G Rand. 2021. Scaling up fact-checking using the wisdom of crowds. Science advances 7, 36 (2021), eabf4393. , Vol. 1, No. 1, Article . Publication date: April 2026. 28 B.Wang and J.Ma et al

2021
[3]

Jacopo Amidei, Paul Piwek, and Alistair Willis. 2018. Rethinking the agreement in human evaluation tasks. In Proceedings of the 27th International Conference on Computational Linguistics. 3318–3329

2018
[4]

Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, and Isabelle Augenstein. 2020. Generating Fact Checking Explanations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault (Eds.). Association for Computational Li...

work page doi:10.18653/v1/2020.acl-main.656 2020
[5]

Do, Yan Xu, and Pascale Fung

Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, Quyet V. Do, Yan Xu, and Pascale Fung. 2023. A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity. InProceedings of the 13th International Joint Conference on Natural Languag...

work page doi:10.18653/v1/2023.ijcnlp-main.45 2023
[6]

On the Opportunities and Risks of Foundation Models

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ B. Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri S. Chatterji, Annie S. Chen, Kathleen Creel, Jared Quincy Davis, Dorottya Demszky, Chris Donahue, Moussa Doumbouya, Esin...

work page internal anchor Pith review Pith/arXiv arXiv 2021
[7]

Carlos Castillo, Marcelo Mendoza, and Barbara Poblete. 2011. Information credibility on twitter. In Proceedings of the 20th international conference on World wide web. 675–684

2011
[8]

Yu, Qiang Yang, and Xing Xie

Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Kaijie Zhu, Hao Chen, Linyi Yang, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, Wei Ye, Yue Zhang, Yi Chang, Philip S. Yu, Qiang Yang, and Xing Xie. 2023. A Survey on Evaluation of Large Language Models. CoRR abs/2307.03109 (2023). https://doi.org/10.48550/arXiv.2307.03109 arXiv:2307.03109

work page doi:10.48550/arxiv.2307.03109 2023
[9]

Harrison Chase. 2022. LangChain. (2022). https://github.com/langchain-ai/langchain

2022
[10]

Jifan Chen, Grace Kim, Aniruddh Sriram, Greg Durrett, and Eunsol Choi. 2024. Complex Claim Verification with Evi- dence Retrieved in the Wild. InProceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), NAACL 2024, Mexico City, Mexico, June 16-21,...

work page doi:10.18653/v1/2024.naacl-long.196 2024
[11]

Jifan Chen, Aniruddh Sriram, Eunsol Choi, and Greg Durrett. 2022. Generating Literal and Implied Subquestions to Fact-check Complex Claims. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, December 7-11, 2022, Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang (Eds.). Asso...

work page doi:10.18653/v1/2022.emnlp- 2022
[12]

Yi Chen, Rui Wang, Haiyun Jiang, Shuming Shi, and Ruifeng Xu. 2023. Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: A Preliminary Empirical Study. CoRR abs/2304.00723 (2023). https://doi.org/10.48550/arXiv.2304.00723 arXiv:2304.00723

work page doi:10.48550/arxiv.2304.00723 2023
[13]

Zhikai Chen, Haitao Mao, Hang Li, Wei Jin, Hongzhi Wen, Xiaochi Wei, Shuaiqiang Wang, Dawei Yin, Wenqi Fan, Hui Liu, and Jiliang Tang. 2023. Exploring the Potential of Large Language Models (LLMs)in Learning on Graphs. SIGKDD Explor. 25, 2 (2023), 42–61. https://doi.org/10.1145/3655103.3655110

work page doi:10.1145/3655103.3655110 2023
[15]

David Cheng-Han Chiang and Hung-yi Lee. 2023. Can Large Language Models Be an Alternative to Human Evalua- tions?. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023, Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (Eds.). Association for Com...

work page doi:10.18653/v1/2023.acl-long.870 2023
[16]

Zhao, Yanping Huang, Andrew M

Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, Dasha Valter, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Y. Zhao, Yanpin...

2024
[17]

Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)

work page internal anchor Pith review Pith/arXiv arXiv 2024
[18]

Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. A survey on rag meeting llms: Towards retrieval-augmented large language models. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 6491–6501

2024
[19]

Bahare Fatemi, Jonathan Halcrow, and Bryan Perozzi. 2024. Talk like a Graph: Encoding Graphs for Large Language Models. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11,

2024
[20]

https://openreview.net/forum?id=IuXR1CCrSi

OpenReview.net. https://openreview.net/forum?id=IuXR1CCrSi
[21]

Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Qianyu Guo, Meng Wang, and Haofen Wang. 2023. Retrieval-Augmented Generation for Large Language Models: A Survey.CoRR abs/2312.10997 (2023). https://doi.org/10.48550/ARXIV.2312.10997 arXiv:2312.10997

work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2312.10997 2023
[22]

Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)

work page internal anchor Pith review Pith/arXiv arXiv 2025
[23]

Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. Retrieval Augmented Language Model Pre-Training. InProceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event (Proceedings of Machine Learning Research, Vol. 119). PMLR, 3929–3938. http://proceedings.mlr. press/v119/guu20a.html

2020
[24]

Beizhe Hu, Qiang Sheng, Juan Cao, Yuhui Shi, Yang Li, Danding Wang, and Peng Qi. 2024. Bad Actor, Good Advi- sor: Exploring the Role of Large Language Models in Fake News Detection. In Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Sy...

work page doi:10.1609/aaai.v38i20.30214 2024
[25]

Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen
[26]

In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022

LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. https://openreview.net/forum?id= nZeVKeeFYf9

2022
[27]

Qisheng Hu, Quanyu Long, and Wenya Wang. 2024. Decomposition Dilemmas: Does Claim Decomposition Boost or Burden Fact-Checking Performance? arXiv:2411.02400 [cs.IR] https://arxiv.org/abs/2411.02400

work page arXiv 2024
[28]

Fan Huang, Haewoon Kwak, and Jisun An. 2023. Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech. InCompanion Proceedings of the ACM Web Conference 2023, WWW 2023, Austin, TX, USA, 30 April 2023 - 4 May 2023, Ying Ding, Jie Tang, Juan F. Sequeda, Lora Aroyo, Carlos Castillo, and Geert-Jan Houben...

work page doi:10.1145/3543873.3587368 2023
[29]

Jin Huang, Xingjian Zhang, Qiaozhu Mei, and Jiaqi Ma. 2023. Can LLMs Effectively Leverage Graph Structural Infor- mation: When and Why. CoRR abs/2309.16595 (2023). https://doi.org/10.48550/ARXIV.2309.16595 arXiv:2309.16595

work page doi:10.48550/arxiv.2309.16595 2023
[30]

Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2025. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems 43, 2 (2025), 1–55

2025
[31]

Yizheng Huang and Jimmy Huang. 2024. A Survey on Retrieval-Augmented Text Generation for Large Language Models. CoRR abs/2404.10981 (2024). https://doi.org/10.48550/ARXIV.2404.10981 arXiv:2404.10981

work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2404.10981 2024
[32]

Gautier Izacard, Patrick S. H. Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2023. Atlas: Few-shot Learning with Retrieval Augmented Language Models. J. Mach. Learn. Res. 24 (2023), 251:1–251:43. https://jmlr.org/papers/v24/23-0037.html

2023
[33]

Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of Hallucination in Natural Language Generation. ACM Comput. Surv. 55, 12 (2023), 248:1–248:38. https://doi.org/10.1145/3571730

work page doi:10.1145/3571730 2023
[34]

Bowen Jin, Gang Liu, Chi Han, Meng Jiang, Heng Ji, and Jiawei Han. 2024. Large Language Models on Graphs: A Comprehensive Survey. IEEE Trans. Knowl. Data Eng. 36, 12 (2024), 8622–8642. https://doi.org/10.1109/TKDE.2024. 3469578

work page doi:10.1109/tkde.2024 2024
[35]

Bowen Jin, Gang Liu, Chi Han, Meng Jiang, Heng Ji, and Jiawei Han. 2024. Large language models on graphs: A comprehensive survey. IEEE Transactions on Knowledge and Data Engineering (2024)

2024
[36]

Zhiwei Jin, Juan Cao, Yongdong Zhang, and Jiebo Luo. 2016. News verification by exploiting conflicting social viewpoints in microblogs. In Proceedings of the AAAI conference on artificial intelligence, Vol. 30

2016
[37]

Neema Kotonya and Francesca Toni. 2020. Explainable Automated Fact-Checking: A Survey. InProceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, , Vol. 1, No. 1, Article . Publication date: April 2026. 30 B.Wang and J.Ma et al. 2020, Donia Scott, Núria Bel, and Chengqing Zong (E...

work page doi:10.18653/v1/2020.coling-main.474 2020
[38]

Neema Kotonya and Francesca Toni. 2020. Explainable Automated Fact-Checking for Public Health Claims. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020, Bonnie Webber, Trevor Cohn, Yulan He, and Yang Liu (Eds.). Association for Computational Linguistics, 7740–7754. https://d...

work page doi:10.18653/v1/2020.emnlp-main.623 2020
[39]

Patrick S. H. Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Hein- rich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval- Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural I...

2020
[40]

Jun Li, Yi Bin, Yunshan Ma, Yang Yang, Zi Huang, and Tat-Seng Chua. 2024. Filter-based Stance Network for Rumor Verification. ACM Trans. Inf. Syst. 42, 4 (2024), 108:1–108:28. https://doi.org/10.1145/3649462

work page doi:10.1145/3649462 2024
[41]

Hao Liao, Jiahao Peng, Zhanyi Huang, Wei Zhang, Guanghua Li, Kai Shu, and Xing Xie. 2023. MUSER: A MUlti-Step Evidence Retrieval Enhancement Framework for Fake News Detection. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023, Long Beach, CA, USA, August 6-10, 2023, Ambuj K. Singh, Yizhou Sun, Leman Akoglu, ...

work page doi:10.1145/3580305.3599873 2023
[42]

Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs/1907.11692 (2019). arXiv:1907.11692 http://arxiv.org/abs/1907.11692

work page internal anchor Pith review Pith/arXiv arXiv 2019
[43]

Yang Liu and Yi-fang Brook Wu. 2020. FNED: A Deep Network for Fake News Early Detection on Social Media. ACM Trans. Inf. Syst. 38, 3 (2020), 25:1–25:33. https://doi.org/10.1145/3386253

work page doi:10.1145/3386253 2020
[44]

Yu Lu, Junwei Bao, Yan Song, Zichen Ma, Shuguang Cui, Youzheng Wu, and Xiaodong He. 2021. RevCore: Review-Augmented Conversational Recommendation. In Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Online Event, August 1-6, 2021 (Findings of ACL, Vol. ACL/IJCNLP 2021), Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli (Ed...

2021
[45]

Yi-Ju Lu and Cheng-Te Li. 2020. GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, Dan Jurafsky, Joyce Chai, Natalie Schluter, and Joel R. Tetreault (Eds.). Association for Computational L...

work page doi:10.18653/v1/2020.acl-main.48 2020
[46]

Joty, and Kam-Fai Wong

Jing Ma, Wei Gao, Shafiq R. Joty, and Kam-Fai Wong. 2019. Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy,July 28- August 2, 2019, Volume1: Long Papers, Anna Korhonen, David R. Traum, and Lluís Mà...

work page doi:10.18653/v1/p19-1244 2019
[47]

Jing Ma, Wei Gao, and Kam-Fai Wong. 2018. Detect Rumor and Stance Jointly by Neural Multi-task Learning. In Companion of the The Web Conference 2018 on The Web Conference 2018, WWW 2018, Lyon , France, April 23-27, 2018, Pierre-Antoine Champin, Fabien Gandon, Mounia Lalmas, and Panagiotis G. Ipeirotis (Eds.). ACM, 585–593. https://doi.org/10.1145/3184558.3188729

work page doi:10.1145/3184558.3188729 2018
[48]

Yuren Mao, Xuemei Dong, Wenyi Xu, Yunjun Gao, Bin Wei, and Ying Zhang. 2025. Fit-rag: Black-box rag with factual information and token reduction. ACM Transactions on Information Systems 43, 2 (2025), 1–27. https: //doi.org/10.1145/367695

work page doi:10.1145/367695 2025
[49]

Qiong Nan, Qiang Sheng, Juan Cao, Beizhe Hu, Danding Wang, and Jintao Li. 2024. Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models. In Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024, Boise, ID, USA, October 21-25, 2024, Edoardo Serra and Francesca Spe...

work page doi:10.1145/3627673.3679519 2024
[50]

Yixin Nie, Haonan Chen, and Mohit Bansal. 2019. Combining Fact Extraction and Verification with Neural Semantic Matching Networks. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artifici...

work page doi:10.1609/aaai.v33i01.33016859 2019
[51]

OpenAI. 2023. GPT-4 Technical Report. CoRR abs/2303.08774 (2023). https://doi.org/10.48550/arXiv.2303.08774 arXiv:2303.08774

work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2303.08774 2023
[52]

Wainwright, Pamela Mishkin, Chong Zhang, Sand- hini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, , Vol

Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sand- hini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, , Vol. 1, No. 1, Article . Publication date: April 2026. A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM ...

2026
[53]

Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sand- hini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F. Christiano, Jan Leike, and Ryan Lowe. 2022. Training language mod- els to follow instructions with...

2022
[54]

Kashyap Popat, Subhabrata Mukherjee, Andrew Yates, and Gerhard Weikum. 2018. DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018, Ellen Riloff, David Chiang, Julia Hockenmaier, and Jun’ic...

work page doi:10.18653/v1/d18-1003 2018
[55]

Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham
[56]

In-Context Retrieval-Augmented Language Models. Trans. Assoc. Comput. Linguistics 11 (2023), 1316–1331. https://doi.org/10.1162/TACL_A_00605

work page doi:10.1162/tacl_a_00605 2023
[57]

Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, November 3-7, 2019, Kentaro Inui, Jing Jiang, Vincen...

work page doi:10.18653/v1/d19-1410 2019
[58]

Parker Riley, Daniel Deutsch, George Foster, Viresh Ratnakar, Ali Dabirmoghaddam, and Markus Freitag. 2024. Finding replicable human evaluations via stable ranking probability. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 4908–4919

2024
[59]

Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. CoRR abs/1910.01108 (2019). arXiv:1910.01108 http://arxiv.org/abs/1910.01108

work page internal anchor Pith review arXiv 2019
[60]

Kai Shu, Limeng Cui, Suhang Wang, Dongwon Lee, and Huan Liu. 2019. dEFEND: Explainable Fake News Detection. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, Anchorage, AK, USA, August 4-8, 2019, Ankur Teredesai, Vipin Kumar, Ying Li, Rómer Rosales, Evimaria Terzi, and George Karypis (Eds.). ACM...

work page doi:10.1145/3292500.3330935 2019
[61]

Miloš Stanojević and Khalil Sima’an. 2014. Beer: Better evaluation as ranking. InProceedings of the Ninth Workshop on Statistical Machine Translation. 414–419

2014
[62]

Jinyan Su, Terry Yue Zhuo, Jonibek Mansurov, Di Wang, and Preslav Nakov. 2023. Fake News Detectors are Biased against Texts Generated by Large Language Models. CoRR abs/2309.08674 (2023). https://doi.org/10.48550/arXiv.2309. 08674 arXiv:2309.08674

work page doi:10.48550/arxiv.2309 2023
[63]

Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, and Chao Huang. 2024. Graphgpt: Graph instruction tuning for large language models. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. 491–500

2024
[64]

Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurélien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. CoRR abs/2302.13971 (2023). https: //doi.org/10.48550/arXiv.2302....

work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2302.13971 2023
[65]

Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)

work page internal anchor Pith review Pith/arXiv arXiv 2023
[66]

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)

2017
[67]

Herun Wan, Shangbin Feng, Zhaoxuan Tan, Heng Wang, Yulia Tsvetkov, and Minnan Luo. 2024. DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection. InFindings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024, Lun-Wei Ku, Andre Martins, and Vivek Srikumar (Eds.). ...

work page doi:10.18653/v1/2024 2024
[68]

Bo Wang, Jing Ma, Hongzhan Lin, Zhiwei Yang, Ruichao Yang, Yuan Tian, and Yi Chang. 2024. Explainable Fake News Detection with Large Language Model via Defense Among Competing Wisdom. In Proceedings of the ACM on Web Conference 2024, WWW 2024, Singapore, May 13-17, 2024, Tat-Seng Chua, Chong-Wah Ngo, Ravi Kumar, Hady W. Lauw, and Roy Ka-Wei Lee (Eds.). AC...

work page doi:10.1145/3589334.3645471 2024
[69]

Rabiul Awal, Kenny Tsu Wei Choo, and Roy Ka-Wei Lee

Han Wang, Ming Shan Hee, Md. Rabiul Awal, Kenny Tsu Wei Choo, and Roy Ka-Wei Lee. 2023. Evaluating GPT-3 Generated Explanations for Hateful Content Moderation. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, 19th-25th August 2023, Macao, SAR, China. ijcai.org, 6255–6263. https://doi.org/10.24963/i...

work page doi:10.24963/ijcai.2023/694 2023
[70]

Haoran Wang and Kai Shu. 2023. Explainable Claim Verification via Knowledge-Grounded Reasoning with Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). Association for Computational Linguistics, 6288–6304. https://doi.org/10.18653...

work page doi:10.18653/v1/2023.findings-emnlp.416 2023
[71]

Jinguang Wang, Shengsheng Qian, Jun Hu, Wenxiang Dong, Xudong Huang, and Richang Hong. 2025. End-to-End Explainable Fake News Detection Via Evidence-Claim Variational Causal Inference.ACM Transactions on Information Systems (2025). https://doi.org/10.1145/3728462

work page doi:10.1145/3728462 2025
[72]

Zehong Wang, Zheyuan Liu, Tianyi Ma, Jiazheng Li, Zheyuan Zhang, Xingbo Fu, Yiyang Li, Zhengqing Yuan, Wei Song, Yijun Ma, et al. 2025. Graph Foundation Models: A Comprehensive Survey. arXiv preprint arXiv:2505.15116 (2025)

work page arXiv 2025
[73]

Junda Wu, Cheng-Chun Chang, Tong Yu, Zhankui He, Jianing Wang, Yupeng Hou, and Julian J. McAuley. 2024. CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation. InProceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024, Barcelona, Spain, August 25-29, 2024, Ricardo Baeza-Yates ...

work page doi:10.1145/3637528.3671901 2024
[74]

Lianwei Wu, Yuan Rao, Ling Sun, and Wangbo He. 2021. Evidence Inference Networks for Interpretable Claim Verifica- tion. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, ...

work page doi:10.1609/aaai 2021
[75]

Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric D

Fan Yang, Shiva K. Pentyala, Sina Mohseni, Mengnan Du, Hao Yuan, Rhema Linder, Eric D. Ragan, Shuiwang Ji, and Xia (Ben) Hu. 2019. XFake: Explainable Fake News Detector with Visualizations. In The World Wide Web Conference, WWW 2019, San Francisco, CA, USA, May 13-17, 2019, Ling Liu, Ryen W. White, Amin Mantrach, Fabrizio Silvestri, Julian J. McAuley, Ric...

work page doi:10.1145/3308558.3314119 2019
[76]

Ruichao Yang, Jing Ma, Hongzhan Lin, and Wei Gao. 2022. A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning. In SIGIR ’22:The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11 - 15, 2022, Enrique Amigó, Pablo Castells, Julio Gon...

work page doi:10.1145/3477495.3531930 2022
[77]

Zhiwei Yang, Jing Ma, Hechang Chen, Hongzhan Lin, Ziyang Luo, and Yi Chang. 2022. A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection. In Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12-17, 2022, Nicoletta Calzolari, Chu-Ren H...

2022
[78]

Ruosong Ye, Caiqi Zhang, Runhui Wang, Shuyuan Xu, and Yongfeng Zhang. 2024. Language is All a Graph Needs. In Findings of the Association for Computational Linguistics: EACL 2024, St. Julian’s,Malta, March 17-22, 2024, Yvette Graham and Matthew Purver (Eds.). Association for Computational Linguistics, 1955–1973. https://aclanthology.org/ 2024.findings-eacl.132

2024
[79]

Zhenrui Yue, Huimin Zeng, Yimeng Lu, Lanyu Shang, Yang Zhang, and Dong Wang. 2024. Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume1: Long Papers), NAACL 2024, Mexico Ci...

work page doi:10.18653/v1/2024.naacl-long.313 2024
[80]

Zhenrui Yue, Huimin Zeng, Lanyu Shang, Yifan Liu, Yang Zhang, and Dong Wang. 2024. Retrieval Augmented Fact Verification by Synthesizing Contrastive Arguments. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024, Lun-Wei Ku, Andre Martins, and V...

work page doi:10.18653/v1/2024.acl-long.556 2024
[81]

Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Yue Xing, Monica Xiao Cheng, and Jiliang Tang. 2024. Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective. CoRR abs/2411.14572 (2024). https://doi.org/10.48550/ARXIV.2411.14572 arXiv:2411.14572 , Vol. 1, No. 1, Ar...

work page doi:10.48550/arxiv.2411.14572 2024

Showing first 80 references.