Dense Retrieval

Follow this topic Ask about this topic

Dense retrieval encodes queries and candidates as vectors, then uses nearest-neighbor search to find relevant results, often where exact keyword matching is inadequate. Common approaches include dual encoders trained with contrastive learning and hard negatives, late-interaction models that match token-level representations, and hybrid systems that combine dense scores with lexical retrieval or reranking. Researchers evaluate these methods on benchmarks such as BEIR and domain-specific tests, while also developing compact indexes, multilingual and specialized retrievers, and retrieval for long documents or agent tasks. A central tension is that stronger models and richer representations can improve difficult or compositional search but cost more to train and serve; generalization, robustness, fairness, and reliable constraint handling remain open challenges.

Latest papers

152 papers17 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Jul 9, 2026

BACH: A Bayesian Admixture of Contrastive Heads for Multi-Interest Two-Tower Retrieval

Two-tower retrievers compress each user into a single embedding, limiting their ability to serve diverse interests. Multi-interest models give each user several heads scored by a maximum inner product, but their hard-routing training under-utilizes heads (routing collapse) and gives no per-user estimate of how much each interest matters for serving. We present BACH (Bayesian Admixture of Contrastive Heads), which casts multi-interest two-tower retrieval as a per-user mixture over the heads, fit by variational inference. The soft mixture trains every head (mitigating collapse), produces a per-user weighting of the interests that is reused at serving, and admits a shared global-codebook variant with precomputable retrieval. On three large-scale benchmarks, MovieLens-20M, Taobao, and Netflix, BACH improves top-of-ranking retrieval over hard-routing multi-interest and single-vector baselines at every head count; we further find that scoring every candidate by its best head, consistent with serving, outperforms the usual target-routed training, and that BACH improves further still.

Quoc Phong Nguyen, Paul Albert, Long Vuong +2

Amazon

Bayesian Mixture Models Multi-Vector Retrieval Information Retrieval Dense Retrieval

Jul 3, 2026

Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls

In many machine learning applications, the most relevant items for a query should be efficiently retrieved. The relevance function is usually an expensive similarity model, making the exhaustive search infeasible. A typical solution is to train another model that separately embeds queries and items to a vector space, where similarity is defined via the dot product or cosine similarity. This allows one to search the relevant items through fast approximate nearest neighbor search at the cost of some reduction in quality. To compensate for this reduction, the found items (candidates) are re-ranked by the expensive ranking model. In this paper, we investigate an alternative approach to candidate selection that utilizes the scores of the expensive model to improve the representations of queries and items. The idea is to describe each query (item) by its relevance to a set of support items (queries) and use these new representations to obtain query (item) embeddings. We theoretically prove that such embeddings are powerful enough to approximate any complex similarity model (under mild conditions). We also investigate the choice of support items, which is a crucial ingredient of the proposed approach. The experiments on diverse academic and production datasets illustrate the power of our method.

Kirill Shevkunov, Andrey Ploskonosov, Liudmila Prokhorenkova

1Yandex.

Learning to Rank Information Retrieval Dense Retrieval

Jul 1, 2026

Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval

The two-tower model has been widely used for large-scale recommendation systems, particularly in the retrieval stage. Industry standards for training two-tower models typically involve in-batch and/or out-of-batch negative sampling. However, these methods often produce easy negatives that models can quickly learn, failing to sufficiently challenge the model. To address this issue, a novel self-supervised hard negative sampling technique is proposed that leverages a large language model (LLM) to generate hard negatives from the same cluster during model training. By utilizing the LLM to learn media representations, the proposed approach ensures that the generated negatives are more challenging and informative. This real-time sampling framework is designed for seamless integration into production models, capable of handling billions of training data points with minimal computational complexity. Experiments on public datasets, along with deployment to a large-scale online system, demonstrate that the proposed negative sampling technique outperforms widely used industry methods. Furthermore, analysis in industrial applications reveals that this sampling method can help break inherent feedback loops in recommendations and significantly reduce popularity bias.

Ivan Ji, Liuyi Hu, Harrison +6

Zihao · 1Meta · Xiangjun

Popularity Bias Hard Negative Mining Dense Retrieval

Jun 26, 2026

SHARD: cell-keyed residual splitting for alignment-resistant private dense retrieval

Dense retrieval systems expose document geometry when vector stores are compromised, and a global protective transform can often be aligned from known pairs. We study SHARD, which splits PCA coordinates into a short routing prefix and a residual protected by independent cell-local orthogonal keys. It supports CKKS ciphertext--plaintext reranking but is evaluated as a leakage trade-off, not a cryptographic document-privacy guarantee. Corrected scoring uses centered document coordinates and an uncentered scoring query, preserving raw ranking up to a query-dependent constant. Across ten BEIR/MIRACL configurations it reproduces raw nDCG@10 and recall, whereas centering both sides loses up to 0.080 nDCG. Cell keys spread diffuse known-pair evidence across compartments, but minimum-norm alignment recovers useful signal far below full key rank, so there is no hard de-anonymization threshold. Real CKKS has maximum score error 2.29e-6 and no top-1 flips; block packing cuts query upload by 74--87% but raises in-process p50 latency by 14--26%. In a strengthened GTR case, an unknown key lowers token-F1 from 0.665 to 0.242; a wide prefix and eight pairs restore much. Under 25--90% release overlap, the unchanged prefix and clean residual norm link persistent rows with R@1 at least 0.9996, although cell-Gram linkage degrades under churn. A formally calibrated Gaussian release gives nDCG@10 at most 0.011 at epsilon=1; its only three strict utility matches occur at epsilon=32768 with linkage R@1 at least 0.995. SHARD preserves retrieval and compartmentalizes alignment evidence, but does not provide DP, unlinkability, or cancellable templates.

Sergey Kurilenko

Moscow Institute of Physics and Technology

Data Leakage Dense Retrieval

Jun 24, 2026

Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model

Semantic search creates an asymmetric disclosure problem: query embeddings may reveal user intent, while returning exact provider vectors distributes reusable representations. We evaluate a deliberately restricted hybrid design. A public corpus-fitted SVD basis and PQ index support client-side candidate selection; candidate IDs are disclosed, while the projected query is encrypted with CKKS. A block-SIMD kernel scores 100 plaintext provider vectors and returns one ciphertext. At 672 dimensions, median server time falls from 1689.1 to 224.5 ms and response size by a factor of 99.5; provider-only saturation reaches 25.99 requests/s with 16 workers. In a frozen post-exploratory revision-analysis subset, disjoint from validation and containing 3,235 canonical BEIR queries, five of six collections satisfy a +/-0.002 nDCG@10 equivalence rule between actual CKKS and plaintext reranking of the same shortlist, while ArguAna is inconclusive. Projection controls favor SVD over random and coordinate truncation. Leakage audits show that disclosed candidate sets are highly linkable and reproduce part of the exact neighbourhood, while public PQ reveals approximate corpus geometry. The design therefore conditionally hides numerical query slots, but does not provide semantic-query, document, unlinkability, circuit, or access-pattern privacy.

Sergey Kurilenko

Moscow Institute of Physics and Technology, Dolgoprudny, Moscow Region, Russia.

Semantic Search Hybrid Retrieval Dense Retrieval

Jun 23, 2026

DREAM: Dense Retrieval Embeddings via Autoregressive Modeling

Dense retrieval embedding models are a fundamental component of modern retrieval-based AI systems. Most dense retrievers are trained with contrastive objectives, which require labeled positive and negative document pairs that are often costly and difficult to obtain. In this work, we investigate whether the autoregressive next-token prediction objective of a large language model (LLM) can provide supervision for dense retrieval. The intuition is simple: if a document contains information relevant to a query, conditioning on that document should make the target output easier for the LLM to predict. A key challenge is that the next-token prediction loss is computed inside the LLM, while the retriever is a separate embedding model. To address this challenge, we propose DREAM (Dense Retrieval Embeddings via Autoregressive Modeling), which injects retriever-generated query-document similarity scores into selected attention heads of a frozen LLM. During training, these scores determine how much attention each candidate document receives while the LLM predicts the target output. The resulting prediction loss provides gradients for retriever training through the attention mechanism. We evaluate DREAM on retrieval benchmarks BEIR and RTEB using embedding backbones ranging from 0.5B to 3B parameters. DREAM consistently outperforms existing baselines across different model scales. These results demonstrate that DREAM provides a promising approach for training dense retrievers through autoregressive modeling.

Yixuan Tang, Yi Yang

The Hong Kong University of Science and Technology

Information Retrieval Text Embedding Models Dense Retrieval

Jun 23, 2026

PETRA: Transforming Web Text for Petroleum-Engineering Domain Adaptation

Petroleum-engineering search exposes a supervision gap for strong general retrievers: relevant evidence exists in public web text, but domain relevance labels are scarce. To address this gap, we propose PETRA, a large-scale Petroleum Engineering Text for Retrieval Adaptation dataset and pipeline that converts noisy public web data into a curated domain corpus and synthetic supervision for dense retrieval and reranking. PETRA contains 1.36M curated chunks, approximately 2B token equivalents,

\approx

859k, embedding training rows from

\approx

224k anchors, and roughly 400k teacher-scored reranker candidate rows. Its construction combines high-recall energy-domain curation, an energy-domain classifier with 98.4% test accuracy, chunk-grounded query generation, LLM-written hard negatives, and retrieval-mined candidate lists. PETRA improves first-stage in-domain Normalized Discounted Cumulative Gain (nDCG) from 0.703 to 0.763 through score fusion. Reranker adaptation improves the public Earth Science benchmark by 44% relative and a six-task reasoning-intensive panel by 23%. Failed training recipes show that high train-holdout accuracy on synthetic labels does not predict retrieval gains; retrieval-mined data helps only after being repackaged as teacher-scored candidate lists sampled from the inference-time candidate distribution.

Kirill Dubovikov, Omar El Mansouri, Hachem Madmoun +12

Mohamed bin Zayed University of Artificial Intelligence · Inception AI

Domain Adaptation Synthetic Data Generation LLM Reranking Information Retrieval Dense Retrieval

Jun 23, 2026

Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics

Enterprise text-to-SQL systems often fail before SQL is generated: the model receives the wrong schema context. Modern warehouses contain thousands of tables, abbreviated columns, informal metrics, hidden join conventions, and permission boundaries that are not captured by raw table names. We introduce Schema-First Retrieval, a retrieval layer that embeds catalog metadata rather than warehouse rows. The system indexes five typed catalog objects, tables, columns, metrics, relationships, and query history, using object-specific text templates. At query time, it combines parallel vector search, lineage expansion, cross-encoder reranking, workload memory, and deterministic access-control gates before SQL generation. On CRUSH4SQL (1,534 questions), Schema-First Retrieval reaches 96.4% table recall@20 and cross-encoder reranking adds +11.1 points at column recall@10; against an equally-templated BM25 baseline, semantic retrieval is +32.8 points at table recall@5. On SEDE (857 questions), query history raises table recall@5 from 52.1% to 92.3%. On BIRD (96 questions), schema-first context reduces SQL execution errors from 15.6% to 6.2%, a 2.5x reduction. These results show that catalog selection is a first-class retrieval problem for natural language analytics, not a prompt formatting detail.

Adarsh Agrawal, Shashank Indukuri

Table Retrieval Text-to-SQL Information Retrieval Hybrid Retrieval Dense Retrieval Database Systems+1

Jun 19, 2026

Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders

Dense sentence embeddings are fundamental to modern Retrieval-Augmented Generation (RAG) systems but suffer from a lack of interpretability due to feature superposition. This opacity hinders the alignment of retrieval processes with human intent, as the entangled representations are difficult to analyze or control. In this work, we propose a method to disentangle the dense representations of sentence transformers (e.g., E5) into human-interpretable concepts using Top-k Sparse Autoencoders (SAEs). We demonstrate that these disentangled features align with specific semantic, syntactic, and pragmatic categories. Furthermore, we introduce an activation steering mechanism that allows for precise intervention in the retrieval process. By clamping specific latent features, we show that it is possible to re-rank search results to better align with user constraints without retraining the backbone model. Our findings suggest that SAE-based decomposition offers a viable path toward transparent and steerable neural information retrieval.

Wonseok Shin, Songkuk Kim

Yonsei University

Text Embeddings Sentence Embeddings Representation Disentanglement Sparse Autoencoders Dense Retrieval

Jun 17, 2026

SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval

With the rapid expansion of massive multilingual corpora, Multilingual Information Retrieval (MLIR) has emerged as a critical technology for global information access. MLIR enables users to retrieve semantically relevant documents from multilingual text collections using a single-language query. However, recent multilingual dense retrieval models often exhibit a strong preference for documents in the same language as the query. This leads to severe language bias, where top-ranked results are dominated by documents of specific languages, even when documents in other languages contain more semantically relevant information. To address this issue, we propose SHIFT, a training-free method applicable in the indexing stage. Specifically, SHIFT utilizes parallel translation pairs to estimate a relative language vector for each target language with respect to a source language. Subsequently, SHIFT corrects the language-specific offset by subtracting this relative language vector from document embeddings during indexing. Our comprehensive evaluation across four MLIR benchmarks and diverse dense retrieval models confirms that SHIFT can effectively mitigate language bias and enhance MLIR performance.

Youngjoon Jang, Seongtae Hong, Hyeonseok Moon +1

Department of Computer Science and Engineering, Korea University

Cross-Lingual Representation Alignment Multilingual IR Dense Retrieval Cross-Lingual Transfer

Jun 17, 2026

Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation

Dense retrieval ranks one query vector against one document vector. On long documents, this interface can fail when a short but decisive span is weakened during document encoding before ranking. We study this failure mode as document-side early compression and introduce the Evidence Dilution Index (EDI) to measure how far a document-level representation falls below the strongest chunk-level evidence within the same gold document. Guided by this view, we propose DICE (Document Inference via Chunk Evidence), a training-free document-side strategy that splits documents into chunks, encodes them independently with a frozen model, and aggregates them back into a single vector while preserving the standard one-query-one-document interface. On LongEmbed, DICE improves retrieval across four backbones, with the largest gains on slices beyond 4k tokens: for Dream, Passkey >4k rises from 30.0 to 90.0 and Needle >4k from 23.3 to 74.0. Across 12,779 filtered samples, DICE yields lower EDI than the single-vector baseline in 92.8% of cases. These results establish document-level encoding as a practical and underexplored lever for long-document retrieval.

Shanshan Lyu, Yiwei Wang, Yujun Cai +2

Chongqing University · State Key Laboratory of AI Safety · Institute of Computing Technology, Chinese Academy of Sciences +2

Long-Context Retrieval Document Chunking Embedding Compression Dense Retrieval

Jun 16, 2026

MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

Retrieval-augmented generation (RAG) systems depend critically on how documents are chunked and searched. Fine-grained chunks can improve retrieval precision but expand the search space, increasing latency and cost; larger chunks reduce the number of candidates but make dense similarity less reliable, as the representation for each chunk mixes multiple topics and introduces more semantic noise. This trade-off becomes especially limiting in deep research tasks, where retrieval must be both fast and precise across large, heterogeneous corpora. We introduce MCompassRAG, a metadata-guided retrieval framework that uses topic-level signals as a semantic compass for selecting relevant evidence. Instead of relying only on cosine similarity between queries and noisy chunk embeddings, MCompassRAG enriches chunk representations with topic metadata in the same embedding space and trains a lightweight retriever through LLM-teacher distillation. At inference time, MCompassRAG performs topic-aware retrieval without additional LLM calls, improving both efficiency and evidence quality. Across six complex retrieval benchmarks, MCompassRAG improves information efficiency (IE) by 8.24% on average with over 5 times lower latency than the strongest efficient RAG baselines. Code is available on https://github.com/AmirAbaskohi/MCompassRAG.

Amirhossein Abaskohi, Raymond Li, Gaetano Cimino +3

University of British Columbia · University of Salerno · ServiceNow Research

Retrieval-Augmented Generation Information Retrieval Dense Retrieval

Jun 16, 2026

SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG

Retrieval-augmented generation (RAG) systems must balance retrieval granularity with contextual coherence, a challenge that existing methods address through LLM-guided chunking, single-level context expansion, or hierarchical summarization. These approaches variously depend on costly LLM calls during indexing or retrieval, limit context aggregation to a single granularity level, or introduce information loss through summarization. We present SproutRAG, an attention-guided hierarchical RAG framework that addresses this trade-off by organizing sentence-level chunks into progressively larger but semantically coherent units, using learned inter-sentence attention to construct a binary chunking tree. Unlike prior approaches that rely on external LLMs, fixed context expansion, or lossy summarization, SproutRAG learns which attention heads and layers best capture semantic document structure, enabling multi-granularity retrieval without additional LLM calls or compressed summaries. At retrieval time, SproutRAG uses hierarchical beam search to retrieve candidates at multiple granularities, capturing multi-sentence relevance beyond flat retrieval. The framework is trained end-to-end with a joint objective that improves both embeddings and tree structure. Experiments across four benchmarks spanning scientific, legal, and open-domain settings demonstrate that SproutRAG improves information efficiency (IE) by 6.1% on average over the strongest baseline. Code is available on https://github.com/AmirAbaskohi/SproutRAG.

Amirhossein Abaskohi, Issam H. Laradji, Peter West +1

University of British Columbia · ServiceNow Research

Document Chunking Retrieval-Augmented Generation Information Retrieval Dense Retrieval Structured RAG

Jun 16, 2026

Non-negative Elastic Net Decoding for Information Retrieval

Dense retrieval has become the dominant paradigm in information retrieval, in which each document is scored against a query by the inner product of their vector embeddings, and the top-

k

documents by score are retrieved for this query. However, since each document's score depends solely on the embedding of the query and itself, the retrieval process is oblivious to the content of the entire corpus. Therefore, dense retrieval cannot avoid selecting semantically similar documents from the corpus, which may result in a non-diverse, redundant set of retrieved documents. To this end, we approach retrieval as a joint decoding problem, in which documents are selected as a set with regard to the context of the rest of the corpus. To achieve this, we propose Non-Negative elastic Net (NNN) decoding, which selects documents whose embeddings jointly reconstruct the query embedding as a sparse non-negative linear combination. Our main theoretical result establishes a strict separation between dense retrieval and NNN decoding. For any corpus, every query correctly handled by dense retrieval is also handled by NNN decoding, while on corpora containing correlated documents, NNN decoding additionally handles queries that dense retrieval cannot. Experimental results indicate that applying NNN decoding to frozen embeddings trained for inner-product scoring yields consistent improvements across several benchmarks. Moreover, we introduce an end-to-end training procedure which optimizes the embeddings for NNN decoding, producing significant performance gains surpassing in all metrics and benchmarks compared to dense retrieval. Our work establishes a new paradigm for leveraging dense embeddings in information retrieval, beyond the standard practice of inner-product scoring.

Koki Okajima, Yasutoshi Ida, Tsukasa Yoshida +1

NTT, Inc.

Representation Learning Information Retrieval Text Embedding Models Sparse Coding Dense Retrieval

Jun 16, 2026

Temporal Preference Optimization for Unsupervised Retrieval

Unsupervised dense retrievers offer scalability by learning semantic similarity from unlabeled documents via contrastive learning, but they struggle to capture the temporal relevance, retrieving semantically related but temporally misaligned documents-an important aspect when a document collection spans multiple time periods (e.g., retrieving documents from 2018-2025 for "Who is the president in 2019?" introduces temporal ambiguity). Existing methods rely on supervised training with explicit timestamps, which are not always feasible. We propose TPOUR (Temporal Preference Optimization for Unsupervised Retriever), which uses our novel training method Temporal Retrieval Preference Optimization (TRPO). TRPO reinterprets preference learning in the temporal dimension, guiding the retriever to favor temporally aligned documents. TPOUR further generalizes to unseen time periods via interpolation in a learned time embedding, enabling continuous temporal alignment. Experiments on temporal information retrieval (T-IR), TPOUR outperforms both unsupervised and supervised baselines. Compared to Qwen-Embedding-8B, despite being about 72.7x smaller, TPOUR Contriever improves average nDCG@5 by +4.04 (+12.15%) on explicit and +4.98 (+15.21%) on implicit queries. We provide our code at https://github.com/agwaBom/TPOUR.

HyunJin Kim, Jaejun Shim, Young Jin Kim +1

1Sungkyunkwan University, Suwon, South Korea · 2Microsoft, Redmond, USA

Temporal IR Preference Optimization Dense Retrieval

Jun 15, 2026

Filtered ANN as a Phase Transition: When Selectivity-Estimation Error Causes Plan Regret

A filtered approximate-nearest-neighbor (ANN) query returns the k nearest vectors among those satisfying an attribute predicate P of selectivity s. The best execution strategy -- pre-filter, post-filter, or in-filter -- changes with s, so a system must estimate s and choose. We model this as an argmax over a landscape with phases (regions where each strategy wins) separated by boundaries, and show that selectivity-estimation error produces plan regret -- recall lost versus the oracle strategy -- only in the critical regions around those boundaries. The regret is a wedge of log-width equal to the multiplicative estimation error epsilon and height equal to the local cliff |V'(s*)| epsilon; the flip-margin 1/|V'(s*)| is the condition number of a sibling cardinality-estimation study reappearing as the local boundary theory. The two phase boundaries follow from independent mathematics: order statistics place the post-filter cliff at s ~ k/K, and site percolation places the in-filter cliff at s_c ~ 0.83/M for graph degree M (corpus-size independent). Criticality exists only under a constrained budget B < sqrt(k n). Under pre-registered decision rules we confirm, on synthetic sweeps and real SIFT1M, that regret concentrates ~290x at the boundary and that the regret curves obey a finite-size scaling collapse onto one universal wedge across two decades of corpus size. A real approximate index does not mis-locate the boundary, but a biased cost model opens a persistent miscalibration band that estimation-error robustness cannot fix. The contribution is a characterization, not a new index. Code and the full pre-registration are public.

Madhulatha Mandarapu, Sandeep Kunkunuru

VaidhyaMegha Private Limited, India

Exact Nearest Neighbor Search Regret Minimization Dense Retrieval Approximate Nearest Neighbor Search

Jun 12, 2026

ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion

Fixed-cardinality retrieval injects a constant top-K chunks into the generator regardless of query complexity, causing over-retrieval for narrow queries and under-retrieval for compositional ones. We describe ScoreGate, a lightweight score-space decision mechanism that controls retrieval cardinality at inference time using two scores already produced by the standard pipeline: bi-encoder similarity s_i and cross-encoder reranker score r_i, with no additional model inference calls required. Its core insight is that cross-encoder affirmation can rescue semantically relevant chunks that bi-encoder retrieval ranks poorly due to vocabulary mismatch -- a failure mode unaddressed by fixed-K or single-score thresholding. On MS MARCO (200 dev queries), ScoreGate achieves MRR@10 = 0.401 with 35% fewer retained chunks than Standard Top-K. On an internal benchmark (n=300, Fleiss' kappa=0.87), ScoreGate observed zero false positives (95% CI [96.4%, 100%]) at 97.77-99.34% recall, with 34.8% fewer tokens per query and only 31ms added latency. Results on both MS MARCO and real-world production traffic suggest that adaptive retrieval cardinality can improve retrieval efficiency without degrading retrieval quality.

Karamvir Singh, Arvind Jain

HighLevel, Inc.

Retrieval-Augmented Generation Adaptive Retrieval Dense Retrieval

Jun 11, 2026

When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval

While mixed-language querying is ubiquitous in multilingual communities, the sensitivity of dense retrievers to such queries remains poorly understood. We present a ratio-controlled study on mMARCO that systematically evaluates retrieval performance by varying the mixing proportion of parallel query translations via embedding-level mixing -- constructing mixed queries as an interpolation of monolingual embeddings. Experiments with BGE-M3 demonstrate that an optimal mixing ratio outperforms the best monolingual endpoint in 88/105 cases. We uncover a distinct asymmetry driven by English dominance: mixing is uniformly beneficial when retrieving from non-English document indices, whereas indices containing English are best served by pure English queries. Furthermore, English acts as the strongest mixing partner for every non-English document language. Finally, when controlling for English dominance, mixing gains correlate negatively with typological distance. We conclude that language-mix sensitivity is structured and predictable, and we validate the robustness of these patterns across model families and scales.

Tongyao Zhu, Chao-Ming Huang, Min-Yen Kan

National University of Singapore

Multilingual IR Dense Retrieval

Jun 10, 2026

What Limits Does Quantization Place on Dense Top- $k$ Retrieval? A Theoretical Study

We establish conditions for embedding a corpus of

N

documents as

d

-dimensional vectors such that every

k

-subset

S \subseteq [N]

is realizable as a result of top-

k

retrieval by some query vector. Recent work shows that

d = O(k)

suffices for such embeddings to exist in

\mathbb{R}^d

, independently of

N

. We theoretically prove that this corpus-independent bound is specific to infinite precision. With

B

bits per coordinate, perfect top-

k

retrieval requires

Bd = Ω(k \ln N)

; thus, at any fixed precision, the dimension must grow at least logarithmically with

N

. Specializing to a

\ell_2

-normalized

B

-bit uniform scalar quantization model, we also identify a threshold on the precision

B^{*} = O(\ln \ln N)

below which no dimension suffices, together with two further regimes that bound the feasible

(B, d)

pairs. Our result implies that in practical vector databases and dense retrieval systems where quantization is standard, the embedding dimension and possibly the precision must grow with the corpus size.

Koki Okajima, Tsukasa Yoshida

NTT, Inc.

Information Retrieval Low-Bit Quantization Neural Network Quantization Dense Retrieval

Jun 9, 2026

The Voronoi Bottleneck: Capacity-Aware Dense Retrieval for Product Search

Dense embedding retrieval compresses all relevance information into a single inner product, imposing a fundamental geometric limit -- the Voronoi Bottleneck -- on the number of query-document relevance patterns expressible at fixed embedding dimension (d). We make three contributions. (1) Unified capacity theory. We prove that Voronoi complexity and sign-rank are equivalent for top-1 retrieval, yielding tight dimension bounds and a computable diagnostic, the Capacity Utilization Score (CUS), that predicts per-query retrieval failure with AUC (> 0.8) without relevance labels. (2) Diagnosis. CUS identifies two capacity regimes -- moderate ((δ\gtrsim 1)), where density-aware training yields measurable gains, and vacuous ((δ\ll 1)), where it does not -- giving practitioners an a priori check before investing in retraining. (3) DART training. We introduce AT-DW-InfoNCE, an Adaptive-Temperature Density-Weighted contrastive objective with formally derived optimal weighting (α^* = 2.0). On a 100K-query synthetic product-search corpus with controlled relevance structure, DART improves +1.9 Recall@100 over a same-data InfoNCE baseline ((84.9 \pm 0.0) vs. (83.0 \pm 0.3); 8 seeds, (p < 0.001)), outperforming focal loss and temperature-schedule alternatives. DART requires zero inference-time overhead -- it is a drop-in training objective that improves any dual-encoder system.

Charith Chandra Sai Balne, Rithwik Maramraju, Siddharth Pratap Singh +4

Walmart Global Tech USA · Walmart Global Tech2026 USA

Contrastive Learning Information Retrieval Dense Retrieval

Jun 9, 2026

When More Documents Hurt RAG: Measuring and Reducing Vector Search Dilution with Domain-Scoped Retrieval

Retrieval-augmented generation (RAG) degrades when applied to large, heterogeneous document collections. In RAG systems, dense similarity becomes less discriminative, causing top-

k

retrieval to return semantically similar but contextually incorrect chunks. We refer to this failure mode as vector search dilution. Even under hybrid dense+sparse retrieval, we first observed it in a deployed Wyoming Department of Transportation (WYDOT) system; in a controlled experiment, growing the corpus from 54 to 1,128 documents cut precision@10 by 63% and recall of the answer-bearing document by 23%. Similar patterns were observed in six other DOTs. To diagnose this issue, we introduce MASDR-RAG (Metadata-Scoped Domain Retrieval for RAG) as a controlled testbed over 200 human-validated queries, five LLM backbones, six public benchmark corpora, and two index stacks. In MASDR-RAG, domain scoping is the load-bearing component. We found hard partitioning to be unsafe, whereas training-free soft scoping is safe when the scope structure is real. Furthermore, we can discover these scopes without hand-curated metadata. However, multi-agent orchestration triggers a precision-faithfulness paradox that survives format controls, prompt controls, and blind human evaluation. Based on these varied outcomes, our practical recommendation is simple: soft-scope first, then perform a single synthesis call.

Nabaraj Subedi, Ahmed Abdelaty, Shivanand Venkanna Sheshappanavar

Dept. of Electrical Engineering & Computer Science University of Wyoming, Laramie, WY 82071, USA · Dept. of Civil, Architectural Engineering & Construction Management University of Wyoming, Laramie, WY 82071, USA

Retrieval-Augmented Generation Agentic RAG Information Retrieval RAG Evaluation RAG Robustness Dense Retrieval

Jun 9, 2026

ConvMemory v2: A Recall-Preserving Top-10 Evidence Reranker for Conversational Memory Retrieval

We describe ConvMemory v2, an opt-in token-evidence reranker that sits after the lightweight ConvMemory v1 reranker and reorders only v1's protected top-10 candidate set. v2 is a fine-tuned ms-marco-MiniLM-L-6-v2 cross-encoder (22,713,601 parameters, measured from the released checkpoint) applied to the ten (query, memory) pairs that v1 has already selected; it does not change which ten memories are returned, so Recall@10 and Hit@10 are identical to v1 by construction, not by statistical coincidence. On the LoCoMo conversational memory benchmark (5 seeds, n = 4955 test rows), v2 raises FULL MRR from v1's 0.5824 to 0.6560 (paired bootstrap +0.0734, 95% CI [+0.0645, +0.0827]) and H@1 from 0.4440 to 0.5474. v2 closes most but not all of the gap to a much more expensive full-pool cross-encoder reference (mxbai-rerank-large-v1 over the top-500, MRR 0.6688): on FULL MRR v2 sits 0.013 below mxbai_top500, but on two raw-dense-hard slices (where v1's protected top-10 has higher recall than mxbai's own top-10) v2 exceeds mxbai_top500. A four-arm load-bearing ablation shows candidate-specific memory text is the mechanism: removing, shuffling, or replacing it collapses MRR below raw dense retrieval. v2 is best understood as a standard recall-preserving cascade pattern with LoCoMo-specific fine-tuning, an explicit anti-shortcut inference contract, and disciplined load-bearing analysis; its advantage over mxbai is slice-specific rather than a general dominance claim. This report extends the v1 technical report (arXiv:2605.28062).

Taiheng Pan

School of Computing and Information Systems University of Melbourne

Cross-Encoder Reranking Conversational Memory Learning to Rank Long-Term Conversational Memory Dense Retrieval

Jun 4, 2026

NTILC: Neural Tool Invocation via Learned Compression

Agentic tool-calling language models depend on large registries of callable APIs, functions, and local actions. Placing full tool specifications directly in the prompt incurs a cost that scales linearly with the size of the tool registry, rapidly consuming the context budget. As the registry grows, this leads to higher latency and degrades selection accuracy, particularly due to interference from irrelevant tools. We overcome these limitations by introducing NTILC, a neural tool selection and invocation framework that replaces in-context registry look-up with learned latent retrieval. NTILC maps both user intent and tool specifications into a shared embedding space, enabling tool selection via external retrieval rather than in-context lookup. The language model is conditioned only on the selected tool schema, allowing for precise, constrained argument generation. Central to our approach is a signature-aware composite objective, which augments semantic similarity with constraints derived from tool signatures (e.g., argument schema, type compatibility, and return types). By combining Circle Loss with a Functional Margin Loss, the model enforces separation between tools that are semantically similar but incompatible under their execution signatures. We evaluate NTILC on public tool-selection and function-calling datasets and report context token usage, retrieval accuracy, and selection latency metrics. Across these settings, NTILC reduces context window consumption by over 95% and inference latency by up to 74% compared to long-context ICT baselines.

Andrew Krikorian, Yayuan Li, Jason J. Corso

Department of Robotics University of Michigan Ann Arbor, MI 48104 · Department of ECE University of Michigan Ann Arbor, MI 48104

LLM Inference Acceleration LLM Tool Use LLM Context Management Tool Selection for Language Model Agents Dense Retrieval

Jun 4, 2026

ColBERTSaR: Sparsified ColBERT Index via Product Quantization

While ColBERT is an effective neural retrieval architecture, it requires a heavy index structure to support candidate set retrieval based on approximated token embeddings, gathering and decompressing document token embeddings, and applying the MaxSim operation. Indexes in PLAID and similar ColBERT implementations require five to ten times the disk storage of the original raw text, which limits their scalability. Furthermore, prior work has identified that the gathering and decompression stages are the primary inefficiencies at query time. Limiting the number of document tokens that must be gathered by thresholding and score approximation does not eliminate the need for the entire index to support ad hoc queries. In this work, we propose an embedding quantization approach that turns a ColBERT index into a true inverted index. We show that, theoretically, ColBERT with embedding quantization is equivalent to learned-sparse retrieval except for the scoring mechanism. Empirically, we demonstrate that our index is 50-70% smaller than a one-bit PLAID index while retaining retrieval effectiveness.

Eugene Yang, Andrew Yates, Dawn Lawrie +3

Johns Hopkins University, Baltimore, MD, USA

Vector Quantization Multi-Vector Retrieval Embedding Compression Product Quantization Dense Retrieval

Jun 2, 2026

Training-Free Lexical-Dense Fusion for Conversational-Memory Retrieval

Retrieving the few past turns that answer a new query across long multi-session histories is the retrieval bottleneck behind long-term conversational memory (LoCoMo, LongMemEval). Recent concurrent work, Nano-Memory, shows that scoring a session by the maximum query-turn similarity (late interaction, "Turn Isolation Retrieval") beats mean-pooled session embeddings. We do not claim that effect; we replicate it and ask what a training-free, CPU-only retrieval stage should add around it. We report four findings. (1) Fuse: score-level fusion of the late-interaction dense score with BM25, under a single leave-one-conversation-out weight, adds +8.8 to +17.2 points of LoCoMo Hit@1 over late interaction alone across six encoders (all p<1e-4), reaching Hit@1 0.752 / NDCG@5 0.829 (e5-large-v2), +11.2 pp over BM25. (2) An off-the-shelf web-search cross-encoder reranker over the fused top-10 hurts here, degrading Hit@1 by 6.9 pp (one reranker, one configuration). (3) A pooling-operator ablation shows top-k late interaction matches max-similarity, but a naive smooth-max (log-sum-exp) collapses for half the encoders. (4) The late-minus-early gap is large for all six encoders and tends to be larger for larger ones, while the marginal fusion gain shrinks; on LongMemEval-S, a lexical regime where BM25 saturates, the net fusion gain over BM25 is small and not significant. A per-category analysis frames the gain as a division of labor: dense late interaction helps most on multi-hop and temporal questions but trails BM25 on adversarial ones. The contribution is a controlled, reproducible account of a strong training-free retrieval recipe, not the late-interaction retriever itself (Nano-Memory's). We make no claim to a complete memory architecture; this is a retrieval-stage study.

Christian Lysenstøen

Inland Norway University of Applied Sciences · Visiting student, University of California, Berkeley

Late Interaction Retrieval Lexical Retrieval Long-Term Conversational Memory Hybrid Retrieval Dense Retrieval

Jun 1, 2026

The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents

Retrieval-augmented generative agents rely on retrieval for grounding, yet are typically evaluated on a query-by-query basis. This isolates interactions that are geometrically coupled in a shared embedding space. For example, we show that the high document density required to serve majority interests (e.g., generic "Crime" movies) can geometrically overcrowd the retrieval neighborhood of a semantically similar minority (e.g., "Film Noir"), effectively expelling minority content from top-

k

results. We introduce a formal framework to analyze how such goal collisions in dense retrieval induce fundamental performance limits and emergent fairness issues inherent to spatial crowding. In our static analysis, we demonstrate that for a fixed embedding space, a phase transition occurs where minority user goals suffer a catastrophic collapse in performance as the density of majority goals increases. We then extend this to a dynamic model and derive a non-linear Fokker-Planck equation that governs the evolution of document embeddings as the agent updates them to maximize retrieval accuracy. Our analysis reveals that this local relevance objective triggers an emergent global mechanism that systematically marginalizes minority interests. We prove that such objectives drive the system to self-organize into a state that exclusively serves majority interests. These results provide a theoretical foundation for understanding a critical grounding failure mode in retrieval-augmented agents.

Shwan Ashrafi, Dan Roth

Oracle AI

Fokker–Planck Equation Algorithmic Fairness Mean-Field Theory Agentic RAG Dense Retrieval

Jun 1, 2026

Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors

Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs. Yet annotation protocols may not purely reflect relevance: they select only a subset of documents for labeling, and this selection can favor certain document types over others. We investigate whether supervised bi-encoder retrievers implicitly learn a document-level relevance prior: a query-independent signal encoded in their representation space as a side effect of training on annotated data. We estimate this prior by training simple classifiers on frozen document embeddings and evaluate three state-of-the-art retrievers across multiple IR benchmarks. We find that supervised neural retrievers encode relevance priors that generalize to unseen documents and are consistent across models. These priors create a findability gap: documents with lower prior are systematically harder to retrieve, even when genuinely relevant. This effect appears in supervised dense retrievers but is weaker and less consistent in BM25, and it persists under controlled matched-document comparisons. Using LLM-based explanations, we find that judged-relevant documents tend to be comprehensive, self-contained summaries of mainstream topics, while niche, fragmentary, or highly technical content is often left unjudged. Retrievers internalize this bias, ranking documents with these favored features higher than documents that lack them, independently of their actual relevance. Our findings expose a structural limitation of supervised retrieval: models trained on annotated data do not just learn relevance, but also the implicit document preferences in their training data.

Francisco Valentini, Edgar Altszyler, Martin Fajcik

CONICET-Universidad de Buenos Aires. Instituto de Ciencias de la Computación (ICC). Buenos Aires, Argentina · Quantit, Buenos Aires, Argentina · Brno University of Technology, Brno, Czech Republic

IR Evaluation Dense Retrieval

Jun 1, 2026

Attention Calibration for Position-Fair Dense Retrieval

Dense retrieval compresses a passage into a single vector, but this compression is positionally skewed: early content dominates the embedding, and retrieval degrades when the relevant span appears later. Prior work proposed an inference-time method that counteracts this skew by equalizing the pooling token's attention across passage segments. However, (i) it redistributes attention at a fixed strength, (ii) it forces the pooling token's attention to itself to a fixed basket-level mass despite substantial variation across layers and architectures, and (iii) its effect on retrieval has not been evaluated. We introduce a strength coefficient that interpolates between uncalibrated and fully equalized attention, together with an efficient implementation that reduces peak calibration memory overhead from 5-7 GiB to under 1 MiB. Across three embedding models and two pooling schemes, moderate calibration provides a better retrieval trade-off than full equalization. We introduce a variant that preserves the pooling token's self-attention mass and redistributes only the remaining mass. On a position-aware retrieval benchmark spanning 10 languages and 31 domains, a configuration selected on English FineWeb-PosQ and transferred without tuning reduces position sensitivity in all 16 evaluated length-quartile, model, and retrieval-setting combinations, by up to 43% relative, while improving nDCG@10 by up to 4.8% relative and leaving general retrieval effectiveness on NanoBEIR essentially unchanged. Calibration runs at indexing time, adding no query-time latency. We release our code at github.com/impresso/fair-sentence-transformers

Andrianos Michail, Elias Schuhmacher, Juri Opitz +2

University of Zurich · Zurich, Switzerland

Information Retrieval Attention Mechanisms Dense Retrieval

Jun 1, 2026

RCEM: Robust Conversational Search EMbedder in Distributional Shift

We propose RCEM, a Robust Conversational search EMbedder that is additionally equipped with LLM's query reformulation capability without losing base model's generalization. Unlike prior conversational dense retrieval approaches that learn direct conversation-to-passage matching, RCEM aligns conversations, prepended by special token, to LLM-rewritten queries, while preserving the original embedding space. The unchanged embedding space automatically maps the rewritten-query to the relevant passages. As a result, RCEM (1) reduces overfitting by simplifying the alignment task from long passages to shorter rewritten queries, (2) eliminates the need for conversation-to-passage relevance labels for training, and (3) maintains its original embedding space that allows conversational queries against indexes built by original embedder without rebuilding them. Extensive experiments show that RCEM consistently outperforms prior approaches, achieving up to 30% improvement under distributional shift.

Kilho Son, Paul Hsu, Cha Zhang +1

Microsoft Corporation

Distribution Shift Conversational Search Text Embedding Models Dense Retrieval

May 31, 2026

Semantic Retrieval for Product Search in E-Commerce

Semantic retrieval in e-commerce must handle short, noisy, and colloquial queries over large product catalogs with fine-grained attribute distinctions. We present a Siamese LLM dual-encoder trained through a two-stage pipeline: contrastive learning with a false-negative margin mask to prevent penalization of near-duplicate products, followed by Relative Odds Alignment for Retrieval (ROAR), a preference optimization objective that extends Bradley-Terry to variable-sized graded relevance groups via consecutive odds-ratio margins. The training corpus mirrors this progression - substitute query-product pairs provide coarse semantic supervision in Stage 1 and graded relevance annotations drive fine-grained ranking in Stage 2. The resulting system accurately retrieves exact matches while correctly ordering substitutes and complementary products, with gains confirmed across query-frequency strata and business verticals, and statistical significance validated through live A/B deployment at scale.

Nikhil Kothari, Saksham Samdani, Ritam Mallick +3

Flipkart, India

Learning to Rank Semantic Search E-Commerce Search Information Retrieval Dense Retrieval