RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer
Ranking
Observed public metrics from 1 member.
Merged summary
TL;DR - An arXiv preprint proposing RP-OPSD, an on-policy self-distillation method that focuses privileged supervision on "reasoning pivot" tokens to transfer LLM reasoning ability from English into other languages. It matters because it targets the specific tokens that drive cross-lingual reasoning transfer rather than treating all tokens uniformly.
- Frames target-language reasoning as a mix of surface text generation and "reasoning pivots" — decisions that advance or redirect the reasoning chain — and argues distillation should concentrate on the latter.
- Uses the distributional shift between matched teacher views with and without an English reference solution as an operational proxy to identify pivots, guiding privileged distillation and reference anchoring.
- Reports gains over strong multilingual reasoning baselines and other OPSD variants on math reasoning benchmarks spanning 17 languages and multiple difficulty levels.
- Analysis indicates the method upweights reasoning-control and problem-conditioned state-update tokens while downweighting surface-realization tokens; code is released at github.com/NJUNLP/RP-OPSD.
Sources (1)
RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer
TL;DR - An arXiv preprint proposing RP-OPSD, an on-policy self-distillation method that focuses privileged supervision on "reasoning pivot" tokens to transfer LLM reasoning ability from English into other languages. It matters because it targets the specific tokens that drive cross-lingual reasoning transfer rather than treating all tokens uniformly.
- Frames target-language reasoning as a mix of surface text generation and "reasoning pivots" — decisions that advance or redirect the reasoning chain — and argues distillation should concentrate on the latter.
- Uses the distributional shift between matched teacher views with and without an English reference solution as an operational proxy to identify pivots, guiding privileged distillation and reference anchoring.
- Reports gains over strong multilingual reasoning baselines and other OPSD variants on math reasoning benchmarks spanning 17 languages and multiple difficulty levels.
- Analysis indicates the method upweights reasoning-control and problem-conditioned state-update tokens while downweighting surface-realization tokens; code is released at github.com/NJUNLP/RP-OPSD.