REVIEW 5 cited by
The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT), which leverages the observation of Prefix Self-Consistency -- the shared initial reasoning steps across diverse solution trajectories -- to enhance LLM reasoning efficiency. By training exclusively on the initial prefix substrings (as few as 8 tokens), UPFT removes the need for labeled data or exhaustive sampling. Experiments on reasoning benchmarks show that UPFT matches the performance of supervised methods such as Rejection Sampling Fine-Tuning, while reducing training time by 75% and sampling cost by 99%. Further analysis reveals that errors tend to appear in later stages of the reasoning process and that prefix-based training preserves the model's structural knowledge. This work demonstrates how minimal unsupervised fine-tuning can unlock substantial reasoning gains in LLMs, offering a scalable and resource-efficient alternative to conventional approaches.
Forward citations
Cited by 5 Pith papers
-
LaRe: Latent Refocusing for Multimodal Reasoning
LaRe performs iterative visual refocusing in latent space and reports accuracy gains with fewer tokens, but its main experiments compare against baselines trained with less data.
-
Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning
Selecting the most confident 32-token prefix and completing only it gives better accuracy per compute than majority voting on five math reasoning datasets, using only the model's own confidence as a selector.
-
EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation
Keeping only the first and last parts of chain-of-thought training traces preserves math reasoning accuracy on MATH500 at half the sequence length, but not on harder benchmarks.
-
Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
Enhancing a model's long-context ability before supervised fine-tuning improves math reasoning accuracy, including on short-input benchmarks.
-
MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security
MoGUv2 embeds small routers in the deeper layers of LLMs to dynamically blend a helpful variant and a refusal variant, improving safety against jailbreak and fine-tuning attacks while preserving usability.
Discussion (0). Continue with ORCID to comment.