paper-with-me

Papers

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation

2025-02-27 · Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

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.

📄 PDF Abstract BibTeX arXiv:2502.19830

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityMathematical Reasoning

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

GeoMAD: Geometry-Aware Multi-View Anomaly Detection via Deformable Fusion and Distributional Alignment

2026-08-27 · Shang-Fu Chen, Jhih-Ciang Wu, Kuan-Chuan Peng, Wen-Huang Cheng 외 arxiv

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 Detection

Revisiting Temporal Alignment for Video Restoration

2021-11-30 · CVPR 2022 1 · Kun Zhou, Wenbo Li, Liying Lu, Xiaoguang Han 외

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+2

LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition

2026-05-19 · Yanyu Chen, Jiyue Jiang, Dianzhi Yu, Zheng Wu 외 arxiv

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

2026-06-08 · Grégoire Dhimoïla, Victor Boutin, Agustin Martin Picard, Thomas Fel 외 arxiv

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?

2021-12-01 · NeurIPS 2021 12 · Yuejiang Liu, Parth Kothari, Bastien Van Delft, Baptiste Bellot-Gurlet 외

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