From the 1 of 6 linked papers with an AI index.
6 papers
Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation
Wenbin Wu
The paper audits whether large language models (LLMs) have built‑in preferences for specific assets, using Bitcoin as a case study, and shows that manipulating a discovered interna…
DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networks
Aijie Shu, Wenbin Wu, Gbenga Ibikunle +1
Credit exposure in Decentralized Finance (DeFi) is often implicit and token-mediated, creating a dense web of inter-protocol dependencies. Thus, a shock to one token may result in…
DeXposure-Claw: An Agentic System for DeFi Risk Supervision
Aijie Shu, Bowei Chen, Wenbin Wu +2
Decentralized finance exposes supervisors to fast-moving, networked credit risks. General-purpose LLM agents fit this setting poorly: they over-read weak evidence and recommend hig…
Tokens All the Way Down: A Money View of Decentralized Finance
Wenbin Wu
In traditional banking, repeated deposit-and-lend cycles let a single dollar of reserves support multiple dollars of claims. Decentralized finance produces an analogous structure w…
Aligning to Illusions: Choice Blindness in Human and AI Feedback
Wenbin Wu
Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference…
DeXposure: A Dataset and Benchmarks for Inter-protocol Credit Exposure in Decentralized Financial Networks
Wenbin Wu, Kejiang Qian, Alexis Lui +5
We curate the DeXposure dataset, the first large-scale dataset for inter-protocol credit exposure in decentralized financial networks, covering global markets of 43.7 million entri…