ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
This paper proposes Tree of Evidence (ToE), a hierarchical evidence reasoning framework for automated fact-checking that models each claim as a dynamically expanding argument tree. ToE integrates a reinforcement learning-driven multi-source retrieval agent, an evidence evaluation agent, and an argument tree aggregation algorithm to iteratively decompose, retrieve, and verify claims through an explainable evidence chain. Theoretical analysis guarantees convergence of the retrieval policy, and experiments show improvements of 4 to 24 percentage points over competitive baselines, especially on adversarially poisoned inputs.
[2606.27736] ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
[Submitted on 26 Jun 2026]
Title:ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
View a PDF of the paper titled ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation, by Zhaoqi Wang and 6 other authors
View PDF HTML (experimental)
Abstract:The rapid spread of fake news poses increasing threats to information ecosystems, especially as AI-generated misinformation under Generative Engine Optimization (GEO) poisoning allows adversarially crafted content to be systematically surfaced by retrieval systems, contaminating LLM reasoning. In this paper, we propose Tree of Evidence (ToE), a hierarchical evidence reasoning framework for automated fact-checking that models each claim as a dynamically expanding argument tree. ToE integrates a reinforcement learning-driven multi-source retrieval agent, an evidence evaluation agent, and an argument tree aggregation algorithm to iteratively decompose, retrieve, and verify claims through an explainable evidence chain. We further provide a theoretical analysis of the retrieval process, deriving a formal error bound that guarantees the learned policy converges to a neighborhood of the information-theoretically optimal policy. Experiments across multiple datasets and backbone LLMs demonstrate that ToE achieves improvements ranging from 4 to 24 percentage points over competitive baselines, with particularly pronounced gains on adversarially poisoned inputs.
Subjects:
Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
Cite as: arXiv:2606.27736 [cs.AI]
(or arXiv:2606.27736v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.27736
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Zhaoqi Wang [view email] [v1] Fri, 26 Jun 2026 05:35:27 UTC (3,220 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation, by Zhaoqi Wang and 6 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new | recent | 2026-06
Change to browse by:
cs cs.CR
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)