# Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification

arXiv: https://arxiv.org/abs/2602.11161 · HTML: https://mlsanity.com/paper/2602.11161/

## 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 (most cited first, 15 of 15)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web](https://mlsanity.com/paper/2305.13117/) (2023)
- [Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method](https://mlsanity.com/paper/2310.00305/) (2023)
- [LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification](https://mlsanity.com/paper/2012.13577/) (2020)
- [ReviewFlow: Intelligent Scaffolding to Support Academic Peer Reviewing](https://mlsanity.com/paper/2402.03530/) (2024)
- [HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants](https://mlsanity.com/paper/2509.08494/) (2025)
- [CHECKWHY: Causal Fact Verification via Argument Structure](https://mlsanity.com/paper/2408.10918/) (2024)
- [QA-NatVer: Question Answering for Natural Logic-based Fact Verification](https://mlsanity.com/paper/2310.14198/) (2023)
- [What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering](https://mlsanity.com/paper/1909.09253/) (2019)
- [Abstractive Summarization of Large Document Collections Using GPT](https://mlsanity.com/paper/2310.05690/) (2023)
- [The COVID-19 Infodemic: Can the Crowd Judge Recent Misinformation Objectively?](https://mlsanity.com/paper/2008.05701/) (2020)
- [Dialogues with AI Reduce Beliefs in Misinformation but Build No Lasting Discernment Skills](https://mlsanity.com/paper/2510.01537/) (2025)
- [Bloom: Designing for LLM-Augmented Behavior Change Interactions](https://mlsanity.com/paper/2510.05449/) (2025)
- [The Effects of Interactive AI Design on User Behavior: An Eye-tracking Study of Fact-checking COVID-19 Claims](https://mlsanity.com/paper/2202.08901/) (2022)

## 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.