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

arXiv:2602.11161 · cs.HC, cs.CL · Submitted 2025-12-29 · Read on arXiv

cs.HC, cs.CL

Submitted: 2025-12-29

Updated: 2026-09-21

License: http://creativecommons.org/licenses/by/4.0/

The gist: Fact-checking systems must be scalable and epistemically trustworthy.

Terminology

Verification — 57× in this paper · explained in 2 episodes
Accuracy — 54× in this paper · explained in 1 episode
Scaffolding — 43× in this paper · explained in 3 episodes
Not Enough Evidence — 14× in this paper
Perplexity — 12× in this paper · explained in 3 episodes
Benchmark — 9× in this paper · explained in 2 episodes
Trace — 6× in this paper · explained in 2 episodes
National University of Singapore — 5× in this paper
Analyzer — 4× in this paper · explained in 1 episode
Aggregation — 3× in this paper · explained in 1 episode
Cognitive Load — 3× in this paper · explained in 2 episodes
Affordance — 2× in this paper · explained in 1 episode
Alignment — 2× in this paper · explained in 1 episode
Commentary — 2× in this paper · explained in 2 episodes
Frustration — 2× in this paper · explained in 2 episodes
Modular Components — 2× in this paper · explained in 2 episodes
Prompt Engineering — 2× in this paper · explained in 4 episodes
Abstraction — 1× in this paper · explained in 1 episode
Action Space — 1× in this paper · explained in 1 episode
Actionability — 1× in this paper · explained in 3 episodes
Association of Computing Machinery — 1× in this paper
Explainability — 1× in this paper · explained in 3 episodes
F1 Score — 1× in this paper · explained in 3 episodes
Generalizability — 1× in this paper · explained in 6 episodes
Methodological Rigor — 1× in this paper · explained in 2 episodes
Progressive Disclosure — 1× in this paper · explained in 2 episodes
Reasoning Traces — 1× in this paper · explained in 3 episodes
Redundancy — 1× in this paper · explained in 2 episodes
Robustness — 1× in this paper · explained in 5 episodes
Scaffolding System — 1× in this paper · explained in 2 episodes
Steering — 1× in this paper · explained in 2 episodes
Structured Reasoning — 1× in this paper · explained in 3 episodes
alpha — 1× in this paper · explained in 1 episode

Abstract

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.

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

Terminology

Abstract

Sources

Related papers