Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification
Not on the map. Why?
Abstract (arXiv)
Fact-checking systems must be scalable and epistemically trustworthy. We introduce Althea, a retrieval-augmented system for user-driven claim evaluation that matches standard pipelines on AVeriTeC while improving supported/refuted discrimination. A longitudinal survey experiment (N=961) treats a ten-day follow-up as a fading test: after modeling a verification procedure, we remove the system and ask whether users reproduce it unaided, testing metalearning rather than one-time accuracy. We compare two AI-assisted treatments, Exploratory (guided reasoning) and Summary (synthesized verdicts), against two baselines, unrelated news and Self-search. The treatments yield the strongest immediate accuracy and confidence gains but do not survive the fading test: on unseen claims they perform no better than news, while Self-search, with no procedure to fade, retains a large advantage. This reveals a factchecking-metalearning tradeoff: conditions that most improve immediate accuracy are least likely to produce metalearning, cautioning against treating AI-delivered verdicts as a source of durable literacy gains.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 59 references that are in the map. First posted on arXiv 29 Dec 2025.
Builds on
15 of 59 references.
References · 15
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
- 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
- 2023AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Webcited by 144
- 2023Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Methodcited by 97
- 2020LOREN: Logic-Regularized Reasoning for Interpretable Fact Verificationcited by 16
- 2024ReviewFlow: Intelligent Scaffolding to Support Academic Peer Reviewingcited by 12
- 2025HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistantscited by 11
- 2024CHECKWHY: Causal Fact Verification via Argument Structurecited by 9
- 2023QA-NatVer: Question Answering for Natural Logic-based Fact Verificationcited by 8
- 2019What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answeringcited by 7
- 2023Abstractive Summarization of Large Document Collections Using GPTcited by 6
- 2020The COVID-19 Infodemic: Can the Crowd Judge Recent Misinformation Objectively?cited by 5
3 more
- 2025Dialogues with AI Reduce Beliefs in Misinformation but Build No Lasting Discernment Skillscited by 4
- 2025Bloom: Designing for LLM-Augmented Behavior Change Interactionscited by 3
- 2022The Effects of Interactive AI Design on User Behavior: An Eye-tracking Study of Fact-checking COVID-19 Claimscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task
- 2024FIRE: Fact-checking with Iterative Retrieval and Verification
- 2025Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification
- 2024Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking
- 2026MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment
- 2025SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing
- 2025Fact-checking AI-generated news reports: Can LLMs catch their own lies?
- 2025Hybrid Fact-Checking that Integrates Knowledge Graphs, Large Language Models, and Search-Based Retrieval Agents Improves Interpretable Claim Verification