flâneur

Recent LLMs can use filler tokens or problem repeats to improve (no-CoT) math performance

blog.redwoodresearch.org · 3,685 words · saved by 3 readers

Prior results have shown that LLMs released before 2024 can’t leverage ‘filler tokens’—unrelated tokens prior to the model’s final answer—to perform additional computation and improve performance.1 I did an investigation on more recent models (e.g. Opus 4.5) and found that many recent LLMs improve substantially on math problems when given filler tokens. That is, I force the LLM to answer some math question immediately without being able to reason using Chain-of-Thought (CoT), but do give the LLM filter tokens (e.g., text like “Filler: 1 2 3 ...”) before it has to answer. Giving Opus 4.5 filler tokens2 boosts no-CoT performance from 45% to 51% (p=4e-7) on a dataset of relatively easy (competition) math problems3. I find a similar effect from repeating the problem statement many times, e.g. Opus 4.5’s no-CoT performance is boosted from 45% to 51%. Repeating the problem statement generally works better and is more reliable than filler tokens, especially for relatively weaker models I test

Prior results have shown that LLMs released before 2024 can’t leverage ‘filler tokens’—unrelated tokens prior to the model’s final answer—to perform additional computation and improve performance.1 I did an investigation on more recent models (e.g. Opus 4.5) and found that many recent LLMs improve substantially on math problems when given filler tokens. That is, I force the LLM to answer some math question immediately without being able to reason using Chain-of-Thought (CoT), but do give the LLM filler tokens (e.g., text like “Filler: 1 2 3 ...”) before it has to answer. Giving Opus 4.5…

saved by

related reading