From Outcomes to Mechanisms: A Benchmark for Diagnosing LLM's Mechanism Hallucination on Data Inference Externalities
Open Access
- 8 August 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 9359-9370
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62441230)
- National Natural Science Foundation of China (62172425)
- Scientific Research Innovation Capability Support Project for Young Faculty (SRICSPYF-ZY2025001)
- the Fundamental Research Funds for the Central Universities and the Research Funds of Renmin University of China (22XNKJ04)
- the Fundamental Research Funds for the Central Universities and the Research Funds of Renmin University of China (25XNQZ14)
This publication has 18 references indexed in Scilit:
- LLM-Based Multi-Agent System for Simulating Strategic and Goal-Oriented Data Marketplaces2025
- Generative language models exhibit social identity biasesNature Computational Science, 2024
- Large language models empowered agent-based modeling and simulation: a survey and perspectivesHumanities and Social Sciences Communications, 2024
- The Economics of Digital PrivacyAnnual Review of Economics, 2023
- Price Discrimination in the Information Age: Prices, Poaching, and Privacy with Personalized Targeted DiscountsReview of Economic Studies, 2022
- The economics of social dataThe RAND Journal of Economics, 2022
- The economics of data externalitiesJournal of Economic Theory, 2021
- Markets for Information: An IntroductionAnnual Review of Economics, 2019
- Privacy and personal data collection with information externalitiesJournal of Public Economics, 2019
- The Economics of PrivacyJournal of Economic Literature, 2016