Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG

• URL: http://arxiv.org/abs/2511.09980v1
• Date: Fri, 14 Nov 2025 01:23:44 GMT
• Title: Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG
• Authors: Bo Li, Tian Tian, Zhenghua Xu, Hao Cheng, Shikun Zhang, Wei Ye,
• Abstract summary: We introduce Entropy-Trend Constraint (ETC), a training-free method that determines optimal retrieval timing by modeling the dynamics of token-level uncertainty.<n>ETC consistently outperforms strong baselines while reducing retrieval frequency.<n>It is plug-and-play, model-agnostic, and readily integrable into existing decoding pipelines.
• Score: 35.96258615258145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dynamic retrieval-augmented generation (RAG) allows large language models (LLMs) to fetch external knowledge on demand, offering greater adaptability than static RAG. A central challenge in this setting lies in determining the optimal timing for retrieval. Existing methods often trigger retrieval based on low token-level confidence, which may lead to delayed intervention after errors have already propagated. We introduce Entropy-Trend Constraint (ETC), a training-free method that determines optimal retrieval timing by modeling the dynamics of token-level uncertainty. Specifically, ETC utilizes first- and second-order differences of the entropy sequence to detect emerging uncertainty trends, enabling earlier and more precise retrieval. Experiments on six QA benchmarks with three LLM backbones demonstrate that ETC consistently outperforms strong baselines while reducing retrieval frequency. ETC is particularly effective in domain-specific scenarios, exhibiting robust generalization capabilities. Ablation studies and qualitative analyses further confirm that trend-aware uncertainty modeling yields more effective retrieval timing. The method is plug-and-play, model-agnostic, and readily integrable into existing decoding pipelines. Implementation code is included in the supplementary materials.

Related papers

• Order-Aware Test-Time Adaptation: Leveraging Temporal Dynamics for Robust Streaming Inference [18.524636088926425]
  Test-Time Adaptation (TTA) enables pre-trained models to adjust to distribution shift by learning from unlabeled test-time streams.<n>To address this, we introduce Order-Aware Test-Time Adaptation (OATTA)<n>OATTA consistently boosts established baselines, improving accuracy by up to 6.35%.
  arXiv  Detail & Related papers  (2026-01-28T20:07:40Z)
• Adaptive Evidential Learning for Temporal-Semantic Robustness in Moment Retrieval [39.603000380180774]
  Debiased Evidential Learning for Moment Retrieval (DEMR) is a novel framework that incorporates a Reflective Flipped Fusion (RFF) block for cross-modal alignment.<n>We introduce a Geom-regularizer to refine uncertainty predictions, enabling adaptive alignment with difficult moments and improving retrieval accuracy.
  arXiv  Detail & Related papers  (2025-11-30T16:13:20Z)
• A Weak Penalty Neural ODE for Learning Chaotic Dynamics from Noisy Time Series [7.01848433242846]
  We propose the use of the weak formulation as a complementary approach to the classical strong formulation of data-driven time-series forecasting models.<n>We show that our proposed training strategy, which we coined as the Weak-Penalty NODE (WP-NODE), achieves state-of-the-art forecasting accuracy and exceptional robustness across benchmark chaotic dynamical systems.
  arXiv  Detail & Related papers  (2025-11-10T01:40:35Z)
• Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency [4.047219770183742]
  Time series forecasting plays a pivotal role in critical domains such as energy management and financial markets.<n>This study reveals a counterintuitive phenomenon: appropriately truncating historical data can enhance prediction accuracy.<n>We propose an innovative solution termed Adaptive Masking Loss with Representation Consistency.
  arXiv  Detail & Related papers  (2025-10-22T19:23:53Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• Dynamic Temporal Positional Encodings for Early Intrusion Detection in IoT [3.6686692131754834]
  The rapid expansion of the Internet of Things (IoT) has introduced significant security challenges.<n>Traditional Intrusion Detection Systems (IDS) often overlook the temporal characteristics of network traffic.<n>We propose a Transformer-based Early Intrusion Detection System (EIDS) that incorporates dynamic temporal positional encodings.
  arXiv  Detail & Related papers  (2025-06-22T17:56:19Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• 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)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• A Conditioned Unsupervised Regression Framework Attuned to the Dynamic Nature of Data Streams [0.0]
  This paper presents an optimal strategy for streaming contexts with limited labeled data, introducing an adaptive technique for unsupervised regression. The proposed method leverages a sparse set of initial labels and introduces an innovative drift detection mechanism. To enhance adaptability, we integrate the ADWIN (ADaptive WINdowing) algorithm with error generalization based on Root Mean Square Error (RMSE)
  arXiv  Detail & Related papers  (2023-12-12T19:23:54Z)
• Stochastically forced ensemble dynamic mode decomposition for forecasting and analysis of near-periodic systems [65.44033635330604]
  We introduce a novel load forecasting method in which observed dynamics are modeled as a forced linear system. We show that its use of intrinsic linear dynamics offers a number of desirable properties in terms of interpretability and parsimony. Results are presented for a test case using load data from an electrical grid.
  arXiv  Detail & Related papers  (2020-10-08T20:25:52Z)

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.