Robust Search with Uncertainty-Aware Value Models for Language Model Reasoning

• URL: http://arxiv.org/abs/2502.11155v2
• Date: Sun, 19 Oct 2025 07:53:31 GMT
• Title: Robust Search with Uncertainty-Aware Value Models for Language Model Reasoning
• Authors: Fei Yu, Yingru Li, Benyou Wang,
• Abstract summary: Value model guided search is effective in steering LLM generation but suffers from a lack of robustness.<n>We propose an uncertainty-aware framework with two key components: (1) Uncertainty-Aware Value Models (UVMs), which replace single-point value estimates with value distributions to quantify prediction reliability, and (2) Group Thompson Sampling, an efficient algorithm that selects candidates based on their probability of being optimal.
• Score: 31.973976155760397
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Value model guided search is effective in steering LLM generation but suffers from a lack of robustness. This is due to verifier failure: imperfect VMs mistakenly prune valid reasoning paths, especially when encountering unseen reasoning paths generated during search. To address this, we propose an uncertainty-aware framework with two key components: (1) Uncertainty-Aware Value Models (UVMs), which replace single-point value estimates with value distributions to quantify prediction reliability, and (2) Group Thompson Sampling, an efficient algorithm that selects candidates based on their probability of being optimal. Experiments on two In-Distribution (ID) settings (GSM8K, MATH) and three Out-Of-Distribution (OOD) settings (e.g., AIME25, Minerva Math) show our method significantly mitigates verifier failure and boosts solution coverage, especially on OOD problems. This work provides the first systematic integration of uncertainty quantification into LLM search paradigms, enhancing robustness. The code is released at https://github.com/FreedomIntelligence/UVM.

Related papers

• ProtoDCS: Towards Robust and Efficient Open-Set Test-Time Adaptation for Vision-Language Models [32.840734752367275]
  Prototype-based Double-Check Separation (ProtoDCS) is a robust framework for OSTTA.<n>It separates csID and csOOD samples, enabling safe and efficient adaptation of Vision-Language Models to csID data.<n>ProtoDCS significantly boosts both known-class accuracy and OOD detection metrics.
  arXiv  Detail & Related papers  (2026-02-27T03:39:02Z)
• When LLMs get significantly worse: A statistical approach to detect model degradations [33.63321816712603]
  Minimizing the inference cost and latency of foundation models has become a crucial area of research.<n>We propose a statistically sound hypothesis testing framework based on McNemar's test allowing to efficiently detect model degradations.<n>We find that with our tests even empirical accuracy degradations of 0.3% can be confidently attributed to actual degradations rather than noise.
  arXiv  Detail & Related papers  (2026-02-09T10:45:13Z)
• Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs [72.82403830490084]
  We argue that the decoding rule should be calibrated by correctness, not confidence alone.<n>We propose simple strategies that achieve this goal: Greedy-Threshold makes sampling greedy at very low confidence steps.<n>Together, our findings challenge prevailings about decoding under uncertainty and show gains across math and general reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-07T14:46:12Z)
• Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask [30.819697001992154]
  Large Language Models are a promising tool for automated vulnerability detection.<n>Despite widespread adoption, a critical question remains: Are LLMs truly effective at detecting real-world vulnerabilities?<n>This paper challenges three widely held community beliefs: that LLMs are (i) unreliable, (ii) insensitive to code patches, and (iii) performance-plateaued across model scales.
  arXiv  Detail & Related papers  (2025-04-18T05:32:47Z)
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty [75.1351701045874]
  Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs)<n>We propose self-certainty, a novel and efficient metric that leverages the inherent probability distribution of LLM outputs to estimate response quality without requiring external reward models.<n>Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-02-25T19:08:07Z)
• Scaling Flaws of Verifier-Guided Search in Mathematical Reasoning [16.824343439487617]
  Large language models (LLMs) struggle with multi-step reasoning, where inference-time scaling has emerged as a promising strategy for performance improvement.<n>Verifier-guided search outperforms repeated sampling when sample size is limited by selecting and prioritizing valid reasoning paths.<n>As sample size increases, verifier-guided search exhibits diminishing advantages and eventually underperforms repeated sampling.
  arXiv  Detail & Related papers  (2025-02-01T02:08:49Z)
• A Probabilistic Perspective on Unlearning and Alignment for Large Language Models [48.96686419141881]
  We introduce the first formal probabilistic evaluation framework for Large Language Models (LLMs)<n> Namely, we propose novel metrics with high probability guarantees concerning the output distribution of a model.<n>Our metrics are application-independent and allow practitioners to make more reliable estimates about model capabilities before deployment.
  arXiv  Detail & Related papers  (2024-10-04T15:44:23Z)
• UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation [93.38604803625294]
  We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) We use Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. UncertaintyRAG outperforms baselines by 2.03% on LLaMA-2-7B, achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-03T17:39:38Z)
• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models [79.76293901420146]
  Large Language Models (LLMs) are employed across various high-stakes domains, where the reliability of their outputs is crucial. Our research investigates the fragility of uncertainty estimation and explores potential attacks. We demonstrate that an attacker can embed a backdoor in LLMs, which, when activated by a specific trigger in the input, manipulates the model's uncertainty without affecting the final output.
  arXiv  Detail & Related papers  (2024-07-15T23:41:11Z)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Self-Evaluation Guided Beam Search for Reasoning [61.523627290397556]
  We introduce a stepwise self-evaluation mechanism to guide and calibrate the reasoning process of Large Language Model (LLM) We propose a decoding algorithm integrating the self-evaluation guidance via beam search. Our approach surpasses the corresponding Codex-backboned baselines in few-shot accuracy by $6.34%$, $9.56%$, and $5.46%$ on the GSM8K, AQuA, and StrategyQA.
  arXiv  Detail & Related papers  (2023-05-01T02:37:59Z)
• On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study [14.041071717005362]
  Modern deep models for summarization attains impressive benchmark performance, but they are prone to generating miscalibrated predictive uncertainty. This means that they assign high confidence to low-quality predictions, leading to compromised reliability and trustworthiness in real-world applications. Probabilistic deep learning methods are common solutions to the miscalibration problem, but their relative effectiveness in complex autoregressive summarization tasks are not well-understood.
  arXiv  Detail & Related papers  (2023-04-17T23:06:28Z)
• Model-Based Uncertainty in Value Functions [89.31922008981735]
  We focus on characterizing the variance over values induced by a distribution over MDPs. Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation. We propose a new uncertainty Bellman equation whose solution converges to the true posterior variance over values.
  arXiv  Detail & Related papers  (2023-02-24T09:18:27Z)
• Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts [8.431465371266391]
  Density-Softmax is a sampling-free deterministic framework for uncertainty estimation. We show that our model is the solution of minimax uncertainty risk. Our method enjoys competitive results with state-of-the-art techniques in terms of uncertainty and robustness.
  arXiv  Detail & Related papers  (2023-02-13T16:21:03Z)
• Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization [73.04187954213471]
  We introduce a unified learning approach to simultaneously modeling the coarse- and fine-grained retrieval. The proposed method has achieved +4.03%, +3.38%, and +2.40% Recall@50 accuracy over a strong baseline.
  arXiv  Detail & Related papers  (2022-11-14T14:25:40Z)
• Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval [51.83967175585896]
  UAL aims at providing reliability-aware predictions by considering data uncertainty and model uncertainty simultaneously. Data uncertainty captures the noise" inherent in the sample, while model uncertainty depicts the model's confidence in the sample's prediction.
  arXiv  Detail & Related papers  (2022-10-24T17:53:20Z)
• Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search [12.263913626161155]
  A common type of evaluation is to approximate the adversarial risk of a model as a robustness indicator. We propose AutoLoss-AR, the first method for searching loss functions for tightening the error. The results demonstrate the effectiveness of the proposed methods.
  arXiv  Detail & Related papers  (2021-11-09T11:47:43Z)
• Improving Deterministic Uncertainty Estimation in Deep Learning for Classification and Regression [30.112634874443494]
  We propose a new model that estimates uncertainty in a single forward pass. Our approach combines a bi-Lipschitz feature extractor with an inducing point approximate Gaussian process, offering robust and principled uncertainty estimation.
  arXiv  Detail & Related papers  (2021-02-22T23:29:12Z)
• A Novel Regression Loss for Non-Parametric Uncertainty Optimization [7.766663822644739]
  Quantification of uncertainty is one of the most promising approaches to establish safe machine learning. One of the most commonly used approaches so far is Monte Carlo dropout, which is computationally cheap and easy to apply in practice. We propose a new objective, referred to as second-moment loss ( UCI), to address this issue.
  arXiv  Detail & Related papers  (2021-01-07T19:12:06Z)
• Second-Moment Loss: A Novel Regression Objective for Improved Uncertainties [7.766663822644739]
  Quantification of uncertainty is one of the most promising approaches to establish safe machine learning. One of the most commonly used approaches so far is Monte Carlo dropout, which is computationally cheap and easy to apply in practice. We propose a new objective, referred to as second-moment loss ( UCI), to address this issue.
  arXiv  Detail & Related papers  (2020-12-23T14:17:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.