Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
Self-consistency improves reasoning by aggregating diverse stochastic samples, yet the dynamics behind its efficacy remain underexplored. We reframe self-consistency as a dynamic distributional alignment problem, revealing that decoding temperature not only governs sampling randomness but also actively shapes the latent answer distribution. Given that high temperatures require prohibitively large sample sizes to stabilize, while low temperatures risk amplifying biases, we propose a confidence-driven mechanism that dynamically calibrates temperature: sharpening the sampling distribution under uncertainty to align with high-probability modes, and promoting exploration when confidence is high. Experiments on mathematical reasoning tasks show this approach outperforms fixed-diversity baselines under limited samples, improving both average and best-case performance across varying initial temperatures without additional data or modules. This establishes self-consistency as a synchronization challenge between sampling dynamics and evolving answer distributions.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityMathematical ReasoningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignment
Multi-view anomaly detection (MvAD) detects defects by exploiting complementary observations from multiple camera viewpoints. The central challenge is to fuse views with sufficient geometric awareness while remaining sca…
Anomaly DetectionRevisiting Temporal Alignment for Video Restoration
Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although t…
DeblurringDenoisingMotion CompensationSuper-Resolution+2LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition
The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three chal…
A Unifying Framework for Concept-Based Representational Similarity
Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions. However, concept alignment remains poorly defined: existing approa…
TTT++: When Does Self-Supervised Test-Time Training Fail or Thrive?
Test-time training (TTT) through self-supervised learning (SSL) is an emerging paradigm to tackle distributional shifts. Despite encouraging results, it remains unclear when this approach thrives or fails. In this work, …
Contrastive LearningSelf-Supervised Learning