Pith. sign in

Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A

doi: 10 · 2023 · DOI 10.18653/v1/2023.findings-emnlp.536.https://aclanthology.org/2023.findings-emnlp.536

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
open at publisher browse 1 citing papers

fields

cs.CL 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Self-Guided Test-Time Training for Long-Context LLMs

cs.CL · 2026-07-10 · conditional · novelty 6.0

Model-selected evidence spans for test-time training beat random and full-context TTT on long-context reasoning benchmarks, with up to ~15% relative accuracy gains.

citing papers explorer

Showing 1 of 1 citing paper.

  • Self-Guided Test-Time Training for Long-Context LLMs cs.CL · 2026-07-10 · conditional · none · ref 8

    Model-selected evidence spans for test-time training beat random and full-context TTT on long-context reasoning benchmarks, with up to ~15% relative accuracy gains.