paper-with-me

Papers

Uncertainty-Aware Search and Value Models: Mitigating Search Scaling Flaws in LLMs

2025-02-16 · Fei Yu, Yingru Li, Benyou Wang

Value model-guided search is effective in steering the generation but suffers from scaling flaws: Its superiority diminishes with larger sample sizes, underperforming non-search baselines. This limitation arises from reliability degradation in value models in unseen reasoning paths. To address this, we propose an uncertainty-aware search framework that includes two key components: (1) uncertainty-aware value models that incorporate uncertainty into predictions, and (2) an uncertainty-aware selection process using the proposed efficient Group Thompson Sampling algorithm. Experiments on GSM8K show that our method mitigates search scaling flaws, achieving 90.5% coverage at 16 samples compared to 85.8% for conventional value-guided search. This work establishes the first systematic integration of uncertainty quantification in LLM search paradigms.

📄 PDF Abstract BibTeX arXiv:2502.11155

Code (0)

등록된 구현이 없습니다.

Tasks

GSM8KThompson SamplingUncertainty Quantification

Similar Papers 제목 키워드 기반

Uncertainty Aware AI ML: Why and How

2018-09-20 · Lance Kaplan, Federico Cerutti, Murat Sensoy, Alun Preece 외

This paper argues the need for research to realize uncertainty-aware artificial intelligence and machine learning (AI\&ML) systems for decision support by describing a number of motivating scenarios. Furthermore, the pap…

BIG-bench Machine Learning

Hierarchical Uncertainty-Aware Graph Neural Network

2025-04-28 · Yoonhyuk Choi, Jiho Choi, Taewook Ko, Chong-Kwon Kim

Recent research on graph neural networks (GNNs) has explored mechanisms for capturing local uncertainty and exploiting graph hierarchies to mitigate data sparsity and leverage structural properties. However, the synergis…

DiversityGraph Neural NetworkRepresentation Learning

Uncertainty-aware Distributional Offline Reinforcement Learning

2024-03-26 · Xiaocong Chen, Siyu Wang, Tong Yu, Lina Yao

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties asso…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search

2026-04-07 · Jiahao Zhang, Shaofei Huang, Yaxiong Wang, Zhedong Zheng arxiv

Text-based person search faces inherent limitations due to data scarcity, driven by stringent privacy constraints and the high cost of manual annotation. To mitigate this, existing methods usually rely on a Pretrain-then…

Test-time AdaptationImage RetrievalPerson Search

Uncertainty-Aware Post-Hoc Calibration: Mitigating Confidently Incorrect Predictions Beyond Calibration Metrics

2025-10-19 · Hassan Gharoun, Mohammad Sadegh Khorshidi, Kasra Ranjbarigderi, Fang Chen 외 arxiv

Despite extensive research on neural network calibration, existing methods typically apply global transformations that treat all predictions uniformly, overlooking the heterogeneous reliability of individual predictions.…

Semantic Similarity