Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling
Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling faces challenges in trade-off between sampling budget and reasoning quality. Current strategies remain inefficient as they typically treat sampling width and depth as orthogonal objectives, where width consensus methods risk reinforcing hallucinations, while depth pruning mechanisms prematurely truncate complex yet valid reasoning chains. Therefore, we propose Dual-Dimensional Consistency (DDC), a unified framework that bridges path quality with adaptive termination. By coupling Confidence-Weighted Bayesian protocol with a Trend-Aware Stratified Pruning, our method ensures that computational resources are concentrated on high quality reasoning paths, filtering hallucinations while accelerating consensus. Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Deep Electromagnetic Structure Design Under Limited Evaluation Budgets
Electromagnetic structure (EMS) design plays a critical role in developing advanced antennas and materials, but remains challenging due to high-dimensional design spaces and expensive evaluations. While existing methods …
Differentially Private Covariate Balancing Causal Inference
Differential privacy is the leading mathematical framework for privacy protection, providing a probabilistic guarantee that safeguards individuals' private information when publishing statistics from a dataset. This guar…
Causal InferenceAddressing Data Quality Decompensation in Federated Learning via Dynamic Client Selection
In cross-silo Federated Learning (FL), client selection is critical to ensure high model performance, yet it remains challenging due to data quality decompensation, budget constraints, and incentive compatibility. As tra…
DecompensationFederated LearningDesigning DSIC Mechanisms for Data Sharing in the Era of Large Language Models
Training large language models (LLMs) requires vast amounts of high-quality data from institutions that face legal, privacy, and strategic constraints. Existing data procurement methods often rely on unverifiable trust o…
Privacy PreservingDecoupling Generation and Selection for Budget-Constrained Faithful Summarization
Abstractive summarization models remain vulnerable to factual inconsistency, redundancy, and weak length control. We propose a modular generation-and-selection framework for sentence-budget-constrained summarization. A p…
Multi-Document Summarization