23 papers
TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation
Tianyuan Liang, Xuwei Tan, Lei Shi +6
Tabular data is a primary medium for storing real-world information, driving many industrial applications of machine learning. Traditional predictors achieve strong predictive perf…
PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
Shihao Wang, Xueru Zhang
Applying differential privacy (DP) via DP-SGD to Low-Rank Adaptation (LoRA) is a natural approach for privacy-preserving fine-tuning. However, LoRA's low-rank parameterization pose…
When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop
Yang Zhang, Xiukun Wei, Xueru Zhang
Foundation models are increasingly trained on synthetic data generated by prior model iterations rather than exclusively on real data. This self-consuming training paradigm can lea…
Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection
Xuwei Tan, Yao Ma, Xueru Zhang
Detecting fraud in financial transactions typically relies on tabular models that demand heavy feature engineering to handle high-dimensional data and offer limited interpretabilit…
BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models
Tian Xie, Tongxin Yin, Vaishakh Keshava +2
While large language models (LLMs) play increasingly significant roles in society, research shows they continue to generate content that reflects social bias against sensitive grou…
Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry
Xiukun Wei, Min Shi, Xueru Zhang
Generative model ecosystems increasingly operate as competitive multi-platform markets, where platforms strategically select models from a shared pool and users with heterogeneous…