Context-Aware Search and Retrieval Under Token Erasure

• URL: http://arxiv.org/abs/2604.18424v1
• Date: Mon, 20 Apr 2026 15:42:12 GMT
• Title: Context-Aware Search and Retrieval Under Token Erasure
• Abstract summary: This paper introduces and analyzes a search and retrieval model for RAG-like systems under token erasures.<n>We provide an information-theoretic analysis of remote document retrieval when query representations are only partially preserved.
• Score: 10.728269379368099
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces and analyzes a search and retrieval model for RAG-like systems under {token} erasures. We provide an information-theoretic analysis of remote document retrieval when query representations are only partially preserved. The query is represented using term-frequency-based features, and semantically adaptive redundancy is assigned according to feature importance. Retrieval is performed using TF-IDF-weighted similarity. We characterize the retrieval error probability by showing that the vector of similarity margins converges to a multivariate Gaussian distribution, yielding an explicit approximation and computable upper bounds. Numerical results support the analysis, while a separate data-driven evaluation using embedding-based retrieval on real-world data shows that the same importance-aware redundancy principles extend to modern retrieval pipelines. Overall, the results show that assigning higher redundancy to semantically important query features improves retrieval reliability.

Related papers

• Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation [3.4588983513116065]
  Retrieval quality is the primary bottleneck for accuracy and robustness in retrieval-augmented generation (RAG)<n>We formalize evaluation as a statistical estimation problem, showing that metric reliability is fundamentally limited by the evaluation-set construction.<n>This yields (1) formal coverage guarantees across retrieval semantic regimes and (2) interpretable visibility into retrieval failure modes.
  arXiv  Detail & Related papers  (2026-04-22T16:49:30Z)
• Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage [89.58253972744531]
  Retrieval-augmented generation (RAG) systems combine document retrieval with a generative model to address complex information seeking tasks like report generation.<n>We investigate whether upstream retrieval metrics can serve as reliable early indicators of the final generated response's information coverage.<n>Our findings demonstrate strong correlations between coverage-based retrieval metrics and nugget coverage in generated responses at both topic and system levels.
  arXiv  Detail & Related papers  (2026-03-09T18:20:20Z)
• Rethinking Deep Research from the Perspective of Web Content Distribution Matching [86.90255285277256]
  We propose WeDas, a Web Content Distribution Aware framework that incorporates search-space structural characteristics into the agent's observation space.<n>We introduce a few-shot probing mechanism that iteratively estimates the Query-Result Alignment Score.<n>As a plug-and-play module, WeDas consistently improves sub-goal completion and accuracy across four benchmarks.
  arXiv  Detail & Related papers  (2026-03-07T14:51:17Z)
• Context-Aware Search and Retrieval Over Erasure Channels [12.794591022795355]
  We present an information-theoretic analysis of a remote document retrieval system operating over a symbol erasure channel.<n>The proposed model encodes the feature vector of a query, derived from term-frequency weights of a language corpus.<n>We derive an explicit expression for the retrieval error probability, i.e., the probability under which the less similar document is selected.
  arXiv  Detail & Related papers  (2025-07-16T04:21:46Z)
• 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)
• Generative Retrieval as Multi-Vector Dense Retrieval [71.75503049199897]
  Generative retrieval generates identifiers of relevant documents in an end-to-end manner. Prior work has demonstrated that generative retrieval with atomic identifiers is equivalent to single-vector dense retrieval. We show that generative retrieval and multi-vector dense retrieval share the same framework for measuring the relevance to a query of a document.
  arXiv  Detail & Related papers  (2024-03-31T13:29:43Z)
• BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval [54.66399120084227]
  We propose a novel method to improve the generalization of dense retrieval via capturing matching signal called BERM. Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
  arXiv  Detail & Related papers  (2023-05-18T15:43:09Z)
• Explain like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation [19.922420813509518]
  We introduce the notion of equivalent queries that are generated by maximizing the similarity between the NRM's results and the result set of a sparse retrieval system. We then compare this approach with existing methods such as RM3-based query expansion.
  arXiv  Detail & Related papers  (2023-04-25T07:58:38Z)
• Improving Out-of-Distribution Generalization of Neural Rerankers with Contextualized Late Interaction [52.63663547523033]
  Late interaction, the simplest form of multi-vector, is also helpful to neural rerankers that only use the [] vector to compute the similarity score. We show that the finding is consistent across different model sizes and first-stage retrievers of diverse natures.
  arXiv  Detail & Related papers  (2023-02-13T18:42:17Z)
• Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback [29.719150565643965]
  This paper proposes ANCE-PRF, a new query encoder that uses pseudo relevance feedback (PRF) to improve query representations for dense retrieval. ANCE-PRF uses a BERT encoder that consumes the query and the top retrieved documents from a dense retrieval model, ANCE, and it learns to produce better query embeddings directly from relevance labels. Analysis shows that the PRF encoder effectively captures the relevant and complementary information from PRF documents, while ignoring the noise with its learned attention mechanism.
  arXiv  Detail & Related papers  (2021-08-30T18:10:26Z)
• Generation-Augmented Retrieval for Open-domain Question Answering [134.27768711201202]
  Generation-Augmented Retrieval (GAR) for answering open-domain questions. We show that generating diverse contexts for a query is beneficial as fusing their results consistently yields better retrieval accuracy. GAR achieves state-of-the-art performance on Natural Questions and TriviaQA datasets under the extractive QA setup when equipped with an extractive reader.
  arXiv  Detail & Related papers  (2020-09-17T23:08:01Z)

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.