Frank Rudzicz

I Know It’s Unfair, Do It Anyway: LLM Agents Exploiting Explicitly Unfair Tools for Voluntary Collusion in Strategic Games

SOFTADACLIP: A SMOOTH CLIPPING STRATEGY FOR FAIR AND PRIVATE MODEL TRAINING

Sample-Efficient Differentially Private Fine-Tuning via Gradient Matrix Denoising

Node-Centric Knowledge Graph

When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluation

Filtered not Mixed: Filtering-Based Online Gating for Mixture of Large Language Models

ContraSim: Contrastive Similarity Space Learning for Financial Market Predictions

Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs