Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2606.11907v1
• Date: Wed, 10 Jun 2026 10:37:19 GMT
• Title: Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation
• Abstract summary: We propose Tail-Aware Adaptive-k(TAA-k), a training-free framework that operationalizes Extreme Value Theory (EVT) through a localized validation strategy.<n>Under mild monotone likelihood ratio assumptions, TAA-k yields a stable, query-adaptive cutoff corresponding to the earliest noise-dominated position.<n>Experiments on WebQuestions, 2WikiMultiHopQA, and MuSiQue demonstrate that TAA-k achieves near-oracle retrieval quality (F1 within 2-3% of oracle) with orders-of-magnitude efficiency gains over global EVT methods.
• Score: 0.9786690381850356
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adaptive context selection is critical for retrieval-augmented generation (RAG) systems, as fixed Top-K retrieval fails under query-dependent and heavy-tailed similarity distributions. While Extreme Value Theory (EVT) offers a principled framework for adaptive truncation, existing approaches apply EVT globally across the entire ranked list, incurring prohibitive computational costs and statistical instability. We propose Tail-Aware Adaptive-k(TAA-k), a training-free framework that operationalizes EVT through a localized validation strategy. The key insight is that ranked similarity curves exhibit a characteristic steep--flat--steep pattern reflecting a transition from relevance-dominated to noise-dominated regimes. TAA-k exploits this geometric structure via knee detection to identify a compact candidate region, then applies EVT-based goodness-of-fit testing within this window to validate the onset of tail behavior. This coarse-to-fine design reduces computational complexity from O(N^2M) to O(sqrt{N\log N}*M) while maintaining statistical rigor. Under mild monotone likelihood ratio assumptions, TAA-k yields a stable, query-adaptive cutoff corresponding to the earliest noise-dominated position. Experiments on WebQuestions, 2WikiMultiHopQA, and MuSiQue demonstrate that TAA-k achieves near-oracle retrieval quality (F1 within 2-3% of oracle) with orders-of-magnitude efficiency gains over global EVT methods, while maintaining robustness across embedding models and compression dimensions.

Related papers

• Efficient Conditioning Why Pseudo Observation Batch Bayesian Optimization Works When It Does not [0.0]
  Constant Liar (CL), Kriging Believer (KB), and fantasy models are widely used for batch selection in parallel Bayesian Optimization.<n>We identify efficient conditioning as the key surrogate property the ability to update predictions in closed form when data is augmented.<n>We unify CL, KB, and fantasy models as instances of a single conditioning mechanism differing only in lie value distribution.
  arXiv  Detail & Related papers  (2026-05-12T13:14:24Z)
• FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection [63.91351553178842]
  FACTOR is a training-free Test-time adaptation for Open-vocabulary object detection.<n>It quantifies attribute sensitivity, semantic relevance, and prediction variation to selectively suppress attribute-dependent predictions.<n>Experiments on PASCAL-C, COCO-C, and FoggyCityscapes show that FACTOR consistently outperforms prior TTA methods.
  arXiv  Detail & Related papers  (2026-05-05T02:31:18Z)
• Variational Rectification Inference for Learning with Noisy Labels [74.85528327499662]
  We propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions.<n>VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable.<n>By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function.
  arXiv  Detail & Related papers  (2026-03-18T01:25:08Z)
• ReHARK: Refined Hybrid Adaptive RBF Kernels for Robust One-Shot Vision-Language Adaptation [3.8707695363745214]
  ReHARK is a training-free framework that reinterprets few-shot adaptation through global proximal regularization.<n>A new state-of-the-art for one-shot adaptation is established by ReHARK, which achieves an average accuracy of 65.83%.
  arXiv  Detail & Related papers  (2026-03-12T04:59:09Z)
• Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection [9.337342114768942]
  Training-free video anomaly detection (VAD) has recently emerged as a scalable alternative to supervised approaches.<n>We introduce MM-VAD, a geometry-aware semantic reasoning framework for training free VAD.<n> MM-VAD reframes anomaly detection as adaptive test-time inference rather than fixed feature comparison.
  arXiv  Detail & Related papers  (2026-03-10T09:28:37Z)
• Robust Canonicalization through Bootstrapped Data Re-Alignment [5.437226012505534]
  Fine-grained visual classification tasks, such as insect and bird identification, demand sensitivity to subtle visual cues.<n>We propose a bootstrapping algorithm that iteratively re-aligns training samples by reducing variance.<n>We show that our method consistently outperforms equivariant, and canonicalization baselines while performing on par with augmentation.
  arXiv  Detail & Related papers  (2025-10-09T13:05:20Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• pEBR: A Probabilistic Approach to Embedding Based Retrieval [9.186585413958769]
  Embedding-based retrieval aims to learn a shared semantic representation space for both queries and items.<n>We propose a novel textbfprobabilistic textbfEmbedding-textbfBased textbfRetrieval (textbfpEBR) framework.
  arXiv  Detail & Related papers  (2024-10-25T07:14:12Z)
• ROTI-GCV: Generalized Cross-Validation for right-ROTationally Invariant Data [5.830619388189558]
  Two key tasks in high-dimensional regularized regression are tuning the regularization strength for accurate predictions and estimating the out-of-sample risk.<n>We introduce a new framework, ROTI-GCV, for reliably performing cross-validation under challenging conditions.
  arXiv  Detail & Related papers  (2024-06-17T15:50:00Z)
• Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer [54.32283739486781]
  We present a textbfForgery-aware textbfAdaptive textbfVision textbfTransformer (FA-ViT) under the adaptive learning paradigm. FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation.
  arXiv  Detail & Related papers  (2023-09-20T06:51:11Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• Fine-grained Retrieval Prompt Tuning [149.9071858259279]
  Fine-grained Retrieval Prompt Tuning steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompt and feature adaptation. Our FRPT with fewer learnable parameters achieves the state-of-the-art performance on three widely-used fine-grained datasets.
  arXiv  Detail & Related papers  (2022-07-29T04:10:04Z)

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.