Language Ranker: A Lightweight Ranking framework for LLM Decoding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912669748953088 |
|---|---|
| author | Zhang, Chenheng Du, Tianqi Zhang, Jizhe Xiao, Mingqing Wang, Yifei Wang, Yisen Lin, Zhouchen |
| author_facet | Zhang, Chenheng Du, Tianqi Zhang, Jizhe Xiao, Mingqing Wang, Yifei Wang, Yisen Lin, Zhouchen |
| contents | Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances, such as scaling the computation of inference time with reward models, have underscored the importance of decoding, but these methods often suffer from high computational costs and limited applicability. In this paper, we revisit LLM generation through the lens of recommender systems, conceptualizing the decoding process as analogous to the ranking stage in recommendation pipelines. From this perspective, we observe that both traditional decoding methods and reward models exhibit clear limitations such as redundancy. Motivated by this insight, we propose Language Ranker, a novel framework that introduces a lightweight module to rerank candidate responses using features extracted by the base model. Experiments across a wide range of tasks show that Language Ranker achieves performance comparable to large-scale reward models, while requiring only <0.5M additional parameters, significantly reducing the computational overhead during both training and inference stages. This highlights the efficiency and effectiveness of our method, showcasing its potential to fully unlock the capabilities of LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21883 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Language Ranker: A Lightweight Ranking framework for LLM Decoding Zhang, Chenheng Du, Tianqi Zhang, Jizhe Xiao, Mingqing Wang, Yifei Wang, Yisen Lin, Zhouchen Computation and Language Artificial Intelligence Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances, such as scaling the computation of inference time with reward models, have underscored the importance of decoding, but these methods often suffer from high computational costs and limited applicability. In this paper, we revisit LLM generation through the lens of recommender systems, conceptualizing the decoding process as analogous to the ranking stage in recommendation pipelines. From this perspective, we observe that both traditional decoding methods and reward models exhibit clear limitations such as redundancy. Motivated by this insight, we propose Language Ranker, a novel framework that introduces a lightweight module to rerank candidate responses using features extracted by the base model. Experiments across a wide range of tasks show that Language Ranker achieves performance comparable to large-scale reward models, while requiring only <0.5M additional parameters, significantly reducing the computational overhead during both training and inference stages. This highlights the efficiency and effectiveness of our method, showcasing its potential to fully unlock the capabilities of LLMs. |
| title | Language Ranker: A Lightweight Ranking framework for LLM Decoding |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.21883 |