Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Point-in-Time Financial RAG with Frozen LLMs and Market-Feedback Adaptive Retrieval
Zijie Zhao, Roy E. Welsch
Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets evidence utility depends on event type, forecast horiz…
cs.CL2025
Learning Optimal Prompt Ensemble for Multi-source Visual Prompt Transfer
Enming Zhang, Liwen Cao, Yanru Wu +2
Prompt tuning has emerged as a lightweight strategy for adapting foundation models to downstream tasks, particularly for resource-constrained systems. As pre-trained prompts become…