Dual-Density Inference for Efficient Language Model Reasoning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Zhengyi, Zhang, Shubo, Zhang, Yuxi, Wang, Huimin, Li, Binyang, Wong, Kam-Fai
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914205508042752
author Zhao, Zhengyi
Zhang, Shubo
Zhang, Yuxi
Wang, Huimin
Li, Binyang
Wong, Kam-Fai
author_facet Zhao, Zhengyi
Zhang, Shubo
Zhang, Yuxi
Wang, Huimin
Li, Binyang
Wong, Kam-Fai
contents Large Language Models (LLMs) have shown impressive capabilities in complex reasoning tasks. However, current approaches employ uniform language density for both intermediate reasoning and final answers, leading to computational inefficiency. Our observation found that reasoning process serves a computational function for the model itself, while answering serves a communicative function for human understanding. This distinction enables the use of compressed, symbol-rich language for intermediate computations while maintaining human-readable final explanations. To address this inefficiency, we present Denser: \underline{D}ual-d\underline{ens}ity inf\underline{er}ence, a novel framework that optimizes information density separately for reasoning and answering phases. Our framework implements this through three components: a query processing module that analyzes input problems, a high-density compressed reasoning mechanism for efficient intermediate computations, and an answer generation component that translates compressed reasoning into human-readable solutions. Experimental evaluation across multiple reasoning question answering benchmarks demonstrates that Denser reduces token consumption by up to 62\% compared to standard Chain-of-Thought methods while preserving or improving accuracy. These efficiency gains are particularly significant for complex multi-step reasoning problems where traditional methods generate extensive explanations.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dual-Density Inference for Efficient Language Model Reasoning
Zhao, Zhengyi
Zhang, Shubo
Zhang, Yuxi
Wang, Huimin
Li, Binyang
Wong, Kam-Fai
Computation and Language
Large Language Models (LLMs) have shown impressive capabilities in complex reasoning tasks. However, current approaches employ uniform language density for both intermediate reasoning and final answers, leading to computational inefficiency. Our observation found that reasoning process serves a computational function for the model itself, while answering serves a communicative function for human understanding. This distinction enables the use of compressed, symbol-rich language for intermediate computations while maintaining human-readable final explanations. To address this inefficiency, we present Denser: \underline{D}ual-d\underline{ens}ity inf\underline{er}ence, a novel framework that optimizes information density separately for reasoning and answering phases. Our framework implements this through three components: a query processing module that analyzes input problems, a high-density compressed reasoning mechanism for efficient intermediate computations, and an answer generation component that translates compressed reasoning into human-readable solutions. Experimental evaluation across multiple reasoning question answering benchmarks demonstrates that Denser reduces token consumption by up to 62\% compared to standard Chain-of-Thought methods while preserving or improving accuracy. These efficiency gains are particularly significant for complex multi-step reasoning problems where traditional methods generate extensive explanations.
title Dual-Density Inference for Efficient Language Model Reasoning
topic Computation and Language
url https://arxiv.org/abs/2512.15358