pith. sign in

Solopo: Unlocking long-context capabilities in llms via short-to-long preference optimization.arXiv preprint arXiv:2505.11166

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

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

OPSDL: On-Policy Self-Distillation for Long-Context Language Models

cs.CL · 2026-04-19 · unverdicted · novelty 6.0

OPSDL improves long-context LLM performance by having the model self-distill from its short-context capability using point-wise reverse KL divergence on generated tokens, outperforming SFT and DPO on benchmarks without harming short-context abilities.

citing papers explorer

Showing 1 of 1 citing paper.

  • OPSDL: On-Policy Self-Distillation for Long-Context Language Models cs.CL · 2026-04-19 · unverdicted · none · ref 7 · internal anchor

    OPSDL improves long-context LLM performance by having the model self-distill from its short-context capability using point-wise reverse KL divergence on generated tokens, outperforming SFT and DPO on benchmarks without harming short-context abilities.