StateBench: Testing how language models track state changes over long documents
• 18
AI & ML interests
Building breatkthrough AI to solve the world's biggest problems.
Recent Activity
Papers
Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up
Articles
allenai/20012026-charging-02
bi_yam_follower • Updated • 70 episodes • 265
allenai/19012026-block-03
bi_yam_follower • Updated • 30 episodes • 280
allenai/27012026-untangle-08
bi_yam_follower • Updated • 10 episodes • 216
allenai/28112025-yam-02
bi_yam_follower • Updated • 37 episodes • 276
allenai/28112025-yam-01
bi_yam_follower • Updated • 53 episodes • 274
allenai/27112025-yam-04
bi_yam_follower • Updated • 50 episodes • 240
allenai/27112025-yam-02
bi_yam_follower • Updated • 15 episodes • 261
allenai/27112025-yam-03
bi_yam_follower • Updated • 50 episodes • 273
allenai/27112025-yam-01
bi_yam_follower • Updated • 45 episodes • 241
allenai/26112025-yam-04
bi_yam_follower • Updated • 30 episodes • 236
allenai/26112025-yam-03
bi_yam_follower • Updated • 50 episodes • 263
allenai/26112025-yam-02
bi_yam_follower • Updated • 50 episodes • 271
allenai/26112025-yam-01
bi_yam_follower • Updated • 20 episodes • 272
allenai/25112025-yam-04
bi_yam_follower • Updated • 25 episodes • 267
allenai/25112025-yam-03
bi_yam_follower • Updated • 25 episodes • 243
allenai/25112025-yam-02
bi_yam_follower • Updated • 50 episodes • 290
allenai/25112025-yam-01
bi_yam_follower • Updated • 49 episodes • 258
allenai/24112025-yam-01
bi_yam_follower • Updated • 50 episodes • 690
allenai/27012026-untangle-14
bi_yam_follower • Updated • 20 episodes • 245
allenai/27012026-untangle-13
bi_yam_follower • Updated • 20 episodes • 235
allenai/27012026-untangle-12
bi_yam_follower • Updated • 20 episodes • 275
allenai/27012026-untangle-11
bi_yam_follower • Updated • 20 episodes • 221
allenai/27012026-untangle-10
bi_yam_follower • Updated • 20 episodes • 234
allenai/27012026-untangle-09
bi_yam_follower • Updated • 20 episodes • 249
allenai/27012026-untangle-07
bi_yam_follower • Updated • 20 episodes • 248
allenai/27012026-untangle-06
bi_yam_follower • Updated • 10 episodes • 240
allenai/27012026-untangle-05
bi_yam_follower • Updated • 20 episodes • 228
allenai/27012026-untangle-03
bi_yam_follower • Updated • 20 episodes • 229
allenai/27012026-untangle-04
bi_yam_follower • Updated • 18 episodes • 213
allenai/27012026-untangle-02
bi_yam_follower • Updated • 34 episodes • 245