2 papers
cs.CL2026
Interactive In-Meeting Speaker Correction with Human Feedback
Xinlu He, Yiwen Guan, Badrivishal Paurana +3
Most automatic speech processing systems operate in ``open loop'' mode without user feedback about who said what, yet human-in-the-loop workflows can potentially enable higher accu…
cs.CL2026
Learning to Translate from Soft to Hard LLM Prompts
Pitipat Kongsomjit, Suryansh Goyal, Jacob Whitehill
Soft prompting, also known as continuous prompting, is a parameter-efficient method for tuning LLMs to specific tasks. Like other machine learning techniques, its parameters encode…