paper-with-me

홈 › Papers

Can AI Refute Economic Theory? Evidence from Beyond the Knowledge Cutoff

2026-06-03 · Alexis Akira Toda arxiv

Can artificial intelligence (AI) refute economic theory? I document experiments in which I asked several AI models (Gemini, Refine, Claude, and ChatGPT) to check the correctness of four published papers in economic theory, each containing an error that I helped identify or correct. ChatGPT Pro performed best, occasionally constructing counterexamples and corrected proofs, while other models fared worse. However, no model located a true error without substantial human guidance, and data contamination complicates interpretation. I argue that a competent human paired with a frontier model can outperform current peer review, but AI cannot yet refute economic theory on its own.

📄 PDF Abstract BibTeX arXiv:2606.05383

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Experiments or Outcomes? Probing Scientific Feasibility in Large Language Models

2026-04-20 · Seyedali Mohammadi, Manas Gaur, Francis Ferraro arxiv

Scientific feasibility assessment asks whether a claim is consistent with established knowledge and whether experimental evidence could support or refute it. We frame feasibility assessment as a diagnostic reasoning task…

AI Economist Agent: An Agentic Framework for Model-Grounded Economic Analysis with RAG, Knowledge Graphs, and Large Language Models

2026-06-18 · Masahiro Kato arxiv

We propose a model-grounded RAG-based AI economist with an agentic framework for economic scenario analysis using large language models (LLMs) and knowledge graphs. While LLMs can generate fluent economic narratives, eco…

Knowledge Graphs

Refutation of Spectral Graph Theory Conjectures with Search Algorithms)

2024-09-27 · Milo Roucairol, Tristan Cazenave

We are interested in the automatic refutation of spectral graph theory conjectures. Most existing works address this problem either with the exhaustive generation of graphs with a limited size or with deep reinforcement …

Deep Reinforcement Learningreinforcement-learningReinforcement Learning

Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation

2022-10-25 · Max Glockner, Yufang Hou, Iryna Gurevych

Misinformation emerges in times of uncertainty when credible information is limited. This is challenging for NLP-based fact-checking as it relies on counter-evidence, which may not yet be available. Despite increasing in…

ArticlesFact CheckingMisinformation

A DQN-based Approach to Finding Precise Evidences for Fact Verification

2021-08-01 · ACL 2021 5 · Hai Wan, Haicheng Chen, Jianfeng Du, Weilin Luo 외

Computing precise evidences, namely minimal sets of sentences that support or refute a given claim, rather than larger evidences is crucial in fact verification (FV), since larger evidences may contain conflicting pieces…

Claim VerificationFact VerificationQ-LearningRetrieval