Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908778189815808 |
|---|---|
| author | Ji, Shiyu Wang, Yixuan Liu, Yijun Zhu, Qingfu Che, Wanxiang |
| author_facet | Ji, Shiyu Wang, Yixuan Liu, Yijun Zhu, Qingfu Che, Wanxiang |
| contents | Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token consumption through dynamic self-consistency, they remain constrained by the high latency of sequential requests. In this paper, we propose SeerSC, a dynamic self-consistency framework that simultaneously improves token efficiency and latency by integrating System 1 and System 2 reasoning. Specifically, we utilize the rapid System 1 to compute the answer entropy for given queries. This score is then used to evaluate the potential of samples for scaling, enabling dynamic self-consistency under System 2. Benefiting from the advance and accurate estimation provided by System 1, the proposed method can reduce token usage while simultaneously achieving a significant decrease in latency through parallel generation. It outperforms existing methods, achieving up to a 47% reduction in token consumption and a 43% reduction in inference latency without significant performance loss. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_09345 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling Ji, Shiyu Wang, Yixuan Liu, Yijun Zhu, Qingfu Che, Wanxiang Computation and Language Test-time scaling improves the inference performance of Large Language Models (LLMs) but also incurs substantial computational costs. Although recent studies have reduced token consumption through dynamic self-consistency, they remain constrained by the high latency of sequential requests. In this paper, we propose SeerSC, a dynamic self-consistency framework that simultaneously improves token efficiency and latency by integrating System 1 and System 2 reasoning. Specifically, we utilize the rapid System 1 to compute the answer entropy for given queries. This score is then used to evaluate the potential of samples for scaling, enabling dynamic self-consistency under System 2. Benefiting from the advance and accurate estimation provided by System 1, the proposed method can reduce token usage while simultaneously achieving a significant decrease in latency through parallel generation. It outperforms existing methods, achieving up to a 47% reduction in token consumption and a 43% reduction in inference latency without significant performance loss. |
| title | Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.09345 |