Althea: The Fact-Checking--Metalearning Tradeoff in AI-Assisted Verification
Read the original on arXiv Computation and Language →Althea is a retrieval‑augmented system that supports user‑driven claim evaluation, matching standard pipelines on AVeriTeC while improving discrimination between supported and refuted claims. In a longitudinal survey experiment with 961 participants, two AI‑assisted treatments—Exploratory (guided reasoning) and Summary (synthesized verdicts)—initially boosted accuracy and confidence, but these gains faded after the system was removed, leaving no advantage over unrelated news. In contrast, a Self‑search baseline, which lacks a fading procedure, maintained a significant advantage, highlighting a fact‑checking–metalearning tradeoff where methods that improve immediate accuracy may not foster durable literacy gains.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.