Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"?
Paper
•
2311.09325
•
Published
Tong Liu
tongliuphysics
·
AI & ML interests
None yet
Recent Activity
updated
a model
44 minutes ago
tongliuphysics/qwen3-4b-ins-loopmultiturn6k-granular-rollout8-bs256-0901-step46
published
a model
about 1 hour ago
tongliuphysics/qwen3-4b-ins-loopmultiturn6k-granular-rollout8-bs256-0901-step46
updated
a model
about 7 hours ago
tongliuphysics/qwen3-4b-loopmultiturn5k-binary-rollout8-bs256-0901-step38
Organizations
authored
2
papers
3 months ago
authored
a
paper
about 1 year ago