A Few Tokens Are All You Need
Free while signed in. Answers cite the passages they came from.
Researchers from Tencent AI Lab and The Chinese University of Hong Kong, Shenzhen propose a new approach to boost reasoning in LLMs by only fine-tuning on the first few tokens of generated solutions. Key ideas include:
Prefix Self-Consistency - The authors show that even if different solution paths diverge later, their initial tokens often share core reasoning steps. Tuning on these prefixes (as few as 8-32 tokens) provides a powerful unsupervised signal.
Minimal Token Training - By training only on short prefixes, the method drastically reduces computational cost (up to 16× fewer tokens vs. full-chain fine-tuning) while preserving reasoning structure.
Comparable to Supervised Methods - Despite relying on unsupervised prefixes (no correctness filtering), it matches or exceeds the performance of more compute-heavy methods like Rejection Sampling Fine-Tuning (RFT).
Broad Applicability - It works with different LLM architectures (general-purpose and math-specialized) and scales effectively from small to large custom datasets.
Label-Optional Approach - Works in purely unsupervised mode but can also incorporate ground-truth answer checks if available, further boosting accuracy.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack