Answer Delivery Under a Shared Token Budget: An Audited Study of Stopping and Finalization
Overview & Synopsis
An inference budget is useful only when the system delivers an answer within it. We study a fixed-budget policy combining first-valid-box stopping with a charged finalization cue. On 100 fresh, independently audited GSM8K test questions per model, it improves delivered endpoint accuracy over first-box stopping by 8.0 percentage points for Qwen3-4B-Thinking-2507 and 7.0 for DeepSeek-R1-Distill-Llama-8B. A prelocked repeat on the same questions gives 7.0 and 10.0 points; neither seed shows a gross harm relative to first-box stopping. The point estimates of incremental physical-slot savings are below one percent. A finalization-only ablation separates cue recovery from stopping, and a fixed scalar reader tests extraction as an alternative explanation. The cue is prior art; the contribution is a component and readout analysis with charged injections and verified paths. Results cover two checkpoints, one task, one prompt family, and two fixed seed conditions.
arxiv.org)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | Answer Delivery Under a Shared Token Budget: An Audited Study of Stopping and Finalization |
|---|---|
| Author / Organization | Yupeng Chang, Linyuan Gao, Zhiyuan Li, Yuan Wu, Yi Chang |
| Subject & Discipline | cs.AI |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-273116 |
| Original Source Link | Visit Source Page on arxiv.org » |