5 papers
Optimizing Sparse Outcomes Through Dense Behavioral Signals via Value-Guided Preference Distillation
Ziyi Zhu, Daniel R. Cahn, Thomas D. Hull +4
Aligning multi-turn dialogue agents is usually framed as matching turn-level human preferences, yet direct optimization of long-term outcomes is often ineffective and prone to rewa…
SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration
Ziyi Zhu, Luka Smyth, Saki Shinoda +1
Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do not function as real gradients…
Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue
Olivier Tieleman, Ziyi Zhu, Ting Su +3
Depression is the leading cause of disability worldwide, and early detection of symptom change is essential for timely intervention. Validated instruments such as the Patient Healt…
CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation
Ziyi Zhu, Olivier Tieleman, Alexey Bukhtiyarov +1
LLM-as-judge evaluation has become standard practice for open-ended model assessment; however, judges exhibit systematic biases that cannot be averaged out by increasing the number…
DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation
Ziyi Zhu, Olivier Tieleman, Caitlin A. Stamatis +5
Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate human behavior remains a significant…