Response Time

2 papers across 2 sessions

Poster Session 4

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning

#405 · Timo Kaufmann, Yannick Metz, Daniel Keim, Eyke Hüllermeier

ResponseRank enables data-efficient learning of distance-aware reward models through stratified comparison strength rankings.

Poster Session 6

1 paper

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Preference Learning with Response Time: Robust Losses and Guarantees

#3810 · Ayush Sawarni, Sahasrajit Sarmasarkar, Vasilis Syrgkanis

We offer statistically robust methods for preference learning that leverage response time in the estimation of rewards to yield large improvements in statistical efficiency.