Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Long Multi-session Question Answering on LoCoMo 1.0 (test)

37.5Single-hop F1

No limit

10.66817.63424.631.566Jun 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
37.517.90.724
2026.06
32.316.67.621.4
2026.06
26.515.70.415
2026.06
25.610.12.616.1
2026.06
23.210.19.710.4
2026.06
2312.21.913.2
2026.06
20.510.80.512.7
2026.06
20.212.20.513.4
2026.06
15.513.30.711.2
2026.06
11.710.60.48.6