Sean Cao

Sean Cao, Wei Jiang, Hui Xu

This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock returns or earnings) of LLM outputs leads the LLM to generate biased sentiment and competition measures, even though these measures are intended to be downstream task-independent. Goal-aware prompting shifts intermediate measures toward the disclosed downstream objective. This purpose leakage improves performance before the LLM's knowledge cutoff, but with no advantage post-cutoff. AI bias due to "seeing the goal" is not an algorithmic flaw, but stems from human accountability in research design to ensure the statistical validity and reliability of AI-generated measurements.

Sean Cao, Lin William Cong, Meng Han et al.

Business transactions by public firms are required to be reported, verified, and audited periodically, which is traditionally a labor-intensive and time-consuming process. To streamline this procedure, we design FutureAB (Future Auditing Blockchain) which aims to automate the reporting and auditing process, thereby allowing auditors to focus on discretionary accounts to better detect and prevent fraud. We demonstrate how distributed-ledger technologies build investor trust and disrupt the auditing industry. Our multi-functional design indicates that auditing firms can automate transaction verification without the need for a trusted third party by collaborating and sharing their information while preserving data privacy (commitment scheme) and security (immutability). We also explore how smart contracts and wallets facilitate the computerization and implementation of our system on Ethereum. Finally, performance evaluation reveals the efficacy and scalability of FutureAB in terms of both encryption (0.012 seconds per transaction) and verification (0.001 seconds per transaction).