Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue
Austin M. Y. Cheung, Harsh Vardhan Gupta, Go Nam Lui +3
Memory systems for LLM agents are evaluated mostly on social dialogue, where facts accumulate and rarely change, so remembering reduces largely to finding the turn in which somethi…
cs.CL2026
Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning
Austin MY Cheung, Yi Yang
Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy. We investigate a related but distinct f…