The BERDS Benchmark aims to measure retrieval diversity for questions that are opinionated or invite diverse perspectives.
Hung-Ting Chen
timchen0618
·
AI & ML interests
NLP
Recent Activity
updated a Space 1 day ago
timchen0618/dashboard updated a dataset 1 day ago
timchen0618/browsecomp-plus-scout-runs-budget5-v1 published a dataset 1 day ago
timchen0618/browsecomp-plus-scout-runs-budget5-v1Organizations
datasets 16
timchen0618/browsecomp-plus-scout-runs-budget5-v1
Viewer • Updated • 150 • 8
timchen0618/browsecomp-plus-selected-tools-orig-analysis-v1
Viewer • Updated • 826 • 14
timchen0618/browsecomp-plus-sft-diff-v1
Viewer • Updated • 830 • 57
timchen0618/bcp-full-runs-v1
Viewer • Updated • 4.98k • 165
timchen0618/browsecomp-plus-selected-tools-analysis-v1
Viewer • Updated • 830 • 261
timchen0618/RACA-PROJECT-MANIFEST
Viewer • Updated • 2 • 38
timchen0618/bcp-traj-ext-formatted-v1
Viewer • Updated • 830 • 21.3k
timchen0618/bcp-plan-revisions-v1
Viewer • Updated • 2.06k • 668
timchen0618/browsecomp-plus-trajectories
Viewer • Updated • 15.2k • 5.04k
timchen0618/browsecomp-plus-results
Viewer • Updated • 170 • 55