Tootfinder

Sam Altman claims an "average" ChatGPT query uses about 0.34 watt-hours and about 0.000085 gallons of water, or "roughly one fifteenth of a teaspoon" (Jay Peters/The Verge)
https://www.theverge.com/news/685045/sam-altman-average-cha…

Sam Altman claims an average ChatGPT query uses ‘roughly one fifteenth of a teaspoon’ of water
OpenAI CEO Sam Altman, in a blog post published Tuesday, says an average ChatGPT query uses about 0.000085 gallons of water, or “roughly one fifteenth of a teaspoon.”

OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion
Xian Guo, Ben Chen, Siyuan Wang, Ying Yang, Chenyi Lei, Yuqing Ding, Han Li
https://arxiv.org/abs/2506.06913

OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion
Query suggestion plays a crucial role in enhancing user experience in e-commerce search systems by providing relevant query recommendations that align with users' initial input. This module helps users navigate towards personalized preference needs and reduces typing effort, thereby improving search experience. Traditional query suggestion modules usually adopt multi-stage cascading architectures, for making a well trade-off between system response time and business conversion. But they often s…

QUITE: A Query Rewrite System Beyond Rules with LLM Agents
Yuyang Song, Hanxu Yan, Jiale Lao, Yibo Wang, Yufei Li, Yuanchun Zhou, Jianguo Wang, Mingjie Tang
https://arxiv.org/abs/2506.07675

QUITE: A Query Rewrite System Beyond Rules with LLM Agents
Query rewrite transforms SQL queries into semantically equivalent forms that run more efficiently. Existing approaches mainly rely on predefined rewrite rules, but they handle a limited subset of queries and can cause performance regressions. This limitation stems from three challenges of rule-based query rewrite: (1) it is hard to discover and verify new rules, (2) fixed rewrite rules do not generalize to new query patterns, and (3) some rewrite techniques cannot be expressed as fixed rules. M…

Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
Sezen Per\c{c}in, Xin Su, Qutub Sha Syed, Phillip Howard, Aleksei Kuvshinov, Leo Schwinn, Kay-Ulrich Scholl
https://arxiv.org/abs/2507.06956

Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
Large language models (LLMs) are very costly and inefficient to update with new information. To address this limitation, retrieval-augmented generation (RAG) has been proposed as a solution that dynamically incorporates external knowledge during inference, improving factual consistency and reducing hallucinations. Despite its promise, RAG systems face practical challenges-most notably, a strong dependence on the quality of the input query for accurate retrieval. In this paper, we investigate th…

Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs
Zhixiang Su, Di Wang, Chunyan Miao
https://arxiv.org/abs/2507.07595

Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs
Recent investigations on the effectiveness of Graph Neural Network (GNN)-based models for link prediction in Knowledge Graphs (KGs) show that vanilla aggregation does not significantly impact the model performance. In this paper, we introduce a novel method, named Context Pooling, to enhance GNN-based models' efficacy for link predictions in KGs. To our best of knowledge, Context Pooling is the first methodology that applies graph pooling in KGs. Additionally, Context Pooling is first-of-its-ki…

"[Chain of reasoning] reports are untrustworthy on principle: they are plausible explanations for plausible responses, and since the inferences involved are more complex, they burn more compute and carbon per query as well as introducing more mistakes"
This is a particularly offensive point about #LLMs: we actually do have a class of systems, inference engines, which do reason and can…

Artificial intelligence is the opposite of education
Or: what if there is no middle ground?

JOB-Complex: A Challenging Benchmark for Traditional & Learned Query Optimization
Johannes Wehrstein, Timo Eckmann, Roman Heinrich, Carsten Binnig
https://arxiv.org/abs/2507.07471

JOB-Complex: A Challenging Benchmark for Traditional & Learned Query Optimization
Query optimization is a fundamental task in database systems that is crucial to providing high performance. To evaluate learned and traditional optimizer's performance, several benchmarks, such as the widely used JOB benchmark, are used. However, in this paper, we argue that existing benchmarks are inherently limited, as they do not reflect many real-world properties of query optimization, thus overstating the performance of both traditional and learned optimizers. In fact, simple but realistic…

Optimal Graph Reconstruction by Counting Connected Components in Induced Subgraphs
Hadley Black, Arya Mazumdar, Barna Saha, Yinzhan Xu
https://arxiv.org/abs/2506.08405

Optimal Graph Reconstruction by Counting Connected Components in Induced Subgraphs
The graph reconstruction problem has been extensively studied under various query models. In this paper, we propose a new query model regarding the number of connected components, which is one of the most basic and fundamental graph parameters. Formally, we consider the problem of reconstructing an $n$-node $m$-edge graph with oracle queries of the following form: provided with a subset of vertices, the oracle returns the number of connected components in the induced subgraph. We show $Θ(\frac…

Today I managed to write a #Postgres query using 2 CTEs and a window function to delete some duplicate values (which should have been prevented by a proper unique constraint..) with only a tiny peek into the docs (I forgot the name of the `row_number()` function).

Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
Subhajit Maity, Ayan Kumar Bhunia, Subhadeep Koley, Pinaki Nath Chowdhury, Aneeshan Sain, Yi-Zhe Song
https://arxiv.org/abs/2507.07994

Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
Keypoint detection, integral to modern machine perception, faces challenges in few-shot learning, particularly when source data from the same distribution as the query is unavailable. This gap is addressed by leveraging sketches, a popular form of human expression, providing a source-free alternative. However, challenges arise in mastering cross-modal embeddings and handling user-specific sketch styles. Our proposed framework overcomes these hurdles with a prototypical setup, combined with a gr…

LGND, which uses vector embeddings to analyze geospatial data and has an enterprise app to query it, raised a $9M seed led by Javelin Venture Partners (Tim De Chant/TechCrunch)
https://techcrunch.com/2025/07/10/lgnd-wants-to-make-chatgpt-for-the-earth/

Exclusive: LGND wants to make ChatGPT for the Earth | TechCrunch
LGND has raised $9 million to convert geographic data into vector embeddings to power AI models that understand the Earth.

QUEST: Query Optimization in Unstructured Document Analysis
Zhaoze Sun, Qiyan Deng, Chengliang Chai, Kaisen Jin, Xinyu Guo, Han Han, Ye Yuan, Guoren Wang, Lei Cao
https://arxiv.org/abs/2507.06515

QUEST: Query Optimization in Unstructured Document Analysis
Most recently, researchers have started building large language models (LLMs) powered data systems that allow users to analyze unstructured text documents like working with a database because LLMs are very effective in extracting attributes from documents. In such systems, LLM-based extraction operations constitute the performance bottleneck of query execution due to the high monetary cost and slow LLM inference. Existing systems typically borrow the query optimization principles popular in rel…

This https://arxiv.org/abs/2506.03100 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostly unexplored. In this paper, we propose the first finite-sample generalization bound for RAG in in-context linear regression and derive an exact bias-variance tradeoff. Our framework views the retrieved texts as query-dependent noisy in-context examples and recovers the classical in-context learning (ICL) and standard…

Tight Bound for Quantum Unitary Time-Reversal
Kean Chen, Nengkun Yu, Zhicheng Zhang
https://arxiv.org/abs/2507.05736 https://arxiv.or…

Tight Bound for Quantum Unitary Time-Reversal
Time-reversal of unitary evolution is fundamental in quantum information processing. Many scenarios, particularly those in quantum learning and metrology, assume free access to the time-reverse of an unknown unitary. In this paper, we settle the query complexity of the unitary time-reversal task: approximately implementing $U^{-1}$ given only black-box access to an unknown $d$-dimensional unitary $U$. We provide a tight query lower bound $Ω((1-ε)d^2)$ for the unitary time-reversal to within d…

No Stupid Questions: An Analysis of Question Query Generation for Citation Recommendation
Brian D. Zimmerman, Julien Aubert-B\'educhaud, Florian Boudin, Akiko Aizawa, Olga Vechtomova
https://arxiv.org/abs/2506.08196

No Stupid Questions: An Analysis of Question Query Generation for Citation Recommendation
Existing techniques for citation recommendation are constrained by their adherence to article contents and metadata. We leverage GPT-4o-mini's latent expertise as an inquisitive assistant by instructing it to ask questions which, when answered, could expose new insights about an excerpt from a scientific article. We evaluate the utility of these questions as retrieval queries, measuring their effectiveness in retrieving and ranking masked target documents. In some cases, generated questions end…

Apache Solr 9.8 introduces the LLM module, opening the doors to end-to-end natural language query support through vector-backed semantic search (K Nearest Neighbors). At Berlin Buzzwords 2025, Alessandro Benedetti discussed the open-source contributions from both an indexing and query perspective, as well as what's next for Solr in terms of Large Language Model integration.
Watch the full session here:

DP-SPRT: Differentially Private Sequential Probability Ratio Tests
Thomas Michel, Debabrota Basu, Emilie Kaufmann
https://arxiv.org/abs/2508.06377 https://…

DP-SPRT: Differentially Private Sequential Probability Ratio Tests
We revisit Wald's celebrated Sequential Probability Ratio Test for sequential tests of two simple hypotheses, under privacy constraints. We propose DP-SPRT, a wrapper that can be calibrated to achieve desired error probabilities and privacy constraints, addressing a significant gap in previous work. DP-SPRT relies on a private mechanism that processes a sequence of queries and stops after privately determining when the query results fall outside a predefined interval. This OutsideInterval mecha…

Ich hatte vorhin mal die Idee, im @… nach »Büromaschinen« zu suchen. Es tat sich eine technikgeschichtliche Goldgrube auf: https://archive.org/search?query=bürom

I love how smart these AI technologies are. They understand that "bigger" for cities can be ambiguous, refer to either the population or the area. It's also great that it's showing the sources in the upper corner, and displaying the basic facts.
Small minus on consistency and correctness, but other than that, really a great answer.
#google

Hiding in Plain Sight: Query Obfuscation via Random Multilingual Searches
Anton Firc, Jan Klus\'a\v{c}ek, Kamil Malinka
https://arxiv.org/abs/2506.04963

Hiding in Plain Sight: Query Obfuscation via Random Multilingual Searches
Modern search engines extensively personalize results by building detailed user profiles based on query history and behaviour. While personalization can enhance relevance, it introduces privacy risks and can lead to filter bubbles. This paper proposes and evaluates a lightweight, client-side query obfuscation strategy using randomly generated multilingual search queries to disrupt user profiling. Through controlled experiments on the Seznam.cz search engine, we assess the impact of interleaving…

Testing Isomorphism of Boolean Functions over Finite Abelian Groups
Swarnalipa Datta, Arijit Ghosh, Chandrima Kayal, Manaswi Paraashar, Manmatha Roy
https://arxiv.org/abs/2507.07654

Testing Isomorphism of Boolean Functions over Finite Abelian Groups
Let $f$ and $g$ be Boolean functions over a finite Abelian group $\mathcal{G}$, where $g$ is fully known, and we have {\em query access} to $f$, that is, given any $x \in \mathcal{G}$ we can get the value $f(x)$. We study the tolerant isomorphism testing problem: given $ε\geq 0$ and $τ> 0$, we seek to determine, with minimal queries, whether there exists an automorphism $σ$ of $\mathcal{G}$ such that the fractional Hamming distance between $f \circ σ$ and $g$ is at most $ε$, or whether for…

"This Suits You the Best": Query Focused Comparative Explainable Summarization
Arnav Attri, Anuj Attri, Pushpak Bhattacharyya, Suman Banerjee, Amey Patil, Muthusamy Chelliah, Nikesh Garera
https://arxiv.org/abs/2507.04733

"This Suits You the Best": Query Focused Comparative Explainable Summarization
Product recommendations inherently involve comparisons, yet traditional opinion summarization often fails to provide holistic comparative insights. We propose the novel task of generating Query-Focused Comparative Explainable Summaries (QF-CES) using Multi-Source Opinion Summarization (M-OS). To address the lack of query-focused recommendation datasets, we introduce MS-Q2P, comprising 7,500 queries mapped to 22,500 recommended products with metadata. We leverage Large Language Models (LLMs) to …

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
Ailin Huang, Bingxin Li, Bruce Wang, Boyong Wu, Chao Yan, Chengli Feng, Heng Wang, Hongyu Zhou, Hongyuan Wang, Jingbei Li, Jianjian Sun, Joanna Wang, Mingrui Chen, Peng Liu, Ruihang Miao, Shilei Jiang, Tian Fei, Wang You, Xi Chen, Xuerui Yang, Yechang Huang, Yuxiang Zhang, Zheng Ge, Zheng Gong, Zhewei Huang, Zixin Zhang, Bin Wang, Bo Li, Buyun Ma, Changxin Miao, Changyi Wan, Chen Xu, Dapeng Shi, Dingyuan Hu, Enle…

Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model
Large Audio-Language Models (LALMs) have significantly advanced intelligent human-computer interaction, yet their reliance on text-based outputs limits their ability to generate natural speech responses directly, hindering seamless audio interactions. To address this, we introduce Step-Audio-AQAA, a fully end-to-end LALM designed for Audio Query-Audio Answer (AQAA) tasks. The model integrates a dual-codebook audio tokenizer for linguistic and semantic feature extraction, a 130-billion-parameter…

Modern Minimal Perfect Hashing: A Survey
Hans-Peter Lehmann, Thomas Mueller, Rasmus Pagh, Giulio Ermanno Pibiri, Peter Sanders, Sebastiano Vigna, Stefan Walzer
https://arxiv.org/abs/2506.06536

Modern Minimal Perfect Hashing: A Survey
Given a set $S$ of $n$ keys, a perfect hash function for $S$ maps the keys in $S$ to the first $m \geq n$ integers without collisions. It may return an arbitrary result for any key not in $S$ and is called minimal if $m = n$. The most important parameters are its space consumption, construction time, and query time. Years of research now enable modern perfect hash functions to be extremely fast to query, very space-efficient, and scale to billions of keys. Different approaches give different tr…

Theseus: A Distributed and Scalable GPU-Accelerated Query Processing Platform Optimized for Efficient Data Movement
Felipe Arambur\'u, William Malpica, Kaouther Abrougui, Amin Aramoon, Romulo Auccapuclla, Claude Brisson, Matthijs Brobbel, Colby Farrell, Pradeep Garigipati, Joost Hoozemans, Supun Kamburugamuve, Akhil Nair, Alexander Ocsa, Johan Peltenburg, Rub\'en Quesada L\'opez, Deepak Sihag, Ahmet Uyar, Dhruv Vats, Michael Wendt, Jignesh M. Patel, Rodrigo Arambur\'u

Theseus: A Distributed and Scalable GPU-Accelerated Query Processing Platform Optimized for Efficient Data Movement
Online analytical processing of queries on datasets in the many-terabyte range is only possible with costly distributed computing systems. To decrease the cost and increase the throughput, systems can leverage accelerators such as GPUs, which are now ubiquitous in the compute infrastructure. This introduces many challenges, the majority of which are related to when, where, and how to best move data around the system. We present Theseus -- a production-ready enterprise-scale distributed accelera…

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450 FPS
Wanhua Li, Yujie Zhao, Minghan Qin, Yang Liu, Yuanhao Cai, Chuang Gan, Hanspeter Pfister
https://arxiv.org/abs/2507.07136

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
In this paper, we introduce LangSplatV2, which achieves high-dimensional feature splatting at 476.2 FPS and 3D open-vocabulary text querying at 384.6 FPS for high-resolution images, providing a 42 $\times$ speedup and a 47 $\times$ boost over LangSplat respectively, along with improved query accuracy. LangSplat employs Gaussian Splatting to embed 2D CLIP language features into 3D, significantly enhancing speed and learning a precise 3D language field with SAM semantics. Such advancements in 3D …

Difference Views for Visual Graph Query Building
Benedikt Kantz, Stefan Lengauer, Peter Waldert, Tobias Schreck
https://arxiv.org/abs/2508.05314 https://ar…

Difference Views for Visual Graph Query Building
Knowledge Graphs (KGs) contain vast amounts of linked resources that encode knowledge in various domains, which can be queried and searched for using specialized languages like SPARQL, a query language developed to query KGs. Existing visual query builders enable non-expert users to construct SPARQL queries and utilize the knowledge contained in these graphs. Query building is, however, an iterative and, often, visual process where the question of the user can change and differ throughout the p…

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor
Vatsal Agarwal, Matthew Gwilliam, Gefen Kohavi, Eshan Verma, Daniel Ulbricht, Abhinav Shrivastava
https://arxiv.org/abs/2507.07106

Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor
Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it often can miss fine-grained details that are relevant to the input query. To address these shortcomings, this work studies whether pre-trained text-to-image diffusion models can serve as instruction-aware visual encoders. Through an analysis of their internal re…

Training-Free Query Optimization via LLM-Based Plan Similarity
Nikita Vasilenko, Alexander Demin, Vladimir Boorlakov
https://arxiv.org/abs/2506.05853 https…

Training-Free Query Optimization via LLM-Based Plan Similarity
Large language model (LLM) embeddings offer a promising new avenue for database query optimization. In this paper, we explore how pre-trained execution plan embeddings can guide SQL query execution without the need for additional model training. We introduce LLM-PM (LLM-based Plan Mapping), a framework that embeds the default execution plan of a query, finds its k nearest neighbors among previously executed plans, and recommends database hintsets based on neighborhood voting. A lightweight cons…

Und wurde 1937 bewusst gestrichen: https://digital.wienbibliothek.at/wbrobv/periodical/pageview/1684814?query=hebenstreitplatz

GTRSS: Graph-based Top-$k$ Representative Similar Subtrajectory Query
Mingchang Ge, Liping Wang, Xuemin Lin, Yuang Zhang, Kunming Wang
https://arxiv.org/abs/2507.05542

GTRSS: Graph-based Top-$k$ Representative Similar Subtrajectory Query
Trajectory mining has attracted significant attention. This paper addresses the Top-k Representative Similar Subtrajectory Query (TRSSQ) problem, which aims to find the k most representative subtrajectories similar to a query. Existing methods rely on costly filtering-validation frameworks, resulting in slow response times. Addressing this, we propose GTRSS, a novel Graph-based Top-k Representative Similar Subtrajectory Query framework. During the offline phase, GTRSS builds a dual-layer graph …

This https://arxiv.org/abs/2506.04086 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCG_…

Optimizing Mesh to Improve the Triangular Expansion Algorithm for Computing Visibility Regions
This paper addresses the problem of improving the query performance of the triangular expansion algorithm (TEA) for computing visibility regions by finding the most advantageous instance of the triangular mesh, the preprocessing structure. The TEA recursively traverses the mesh while keeping track of the visible region, the set of all points visible from a query point in a polygonal world. We show that the measured query time is approximately proportional to the number of triangle edge expansio…

This https://arxiv.org/abs/2506.06091 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

MIRIAD: Augmenting LLMs with millions of medical query-response pairs
LLMs are bound to transform healthcare with advanced decision support and flexible chat assistants. However, LLMs are prone to generate inaccurate medical content. To ground LLMs in high-quality medical knowledge, LLMs have been equipped with external knowledge via RAG, where unstructured medical knowledge is split into small text chunks that can be selectively retrieved and integrated into the LLMs context. Yet, existing RAG pipelines rely on raw, unstructured medical text, which can be noisy,…

If you identify as autistic and share an interest in anarchism and syndicalism, you will likely find Rudolf Rocker's writings both accessible and engaging.
Rocker was a prominent German anarchist thinker and activist whose struggle I share common ground with, especially in how he saw the family and marriage as forms of authoritarian control that limit personal freedom.
You can find his collection of writings here:

What I like about the @… built-in LLM answers:
- It's only(!) triggered on request, i.e. when your query ends with a question mark.
- It always admits when it couldn't find good information or there is no clear answer.
- It always cites sources, usually word for word.
I find myself not so much "believing the AI" but rather us…

Local Distance Query with Differential Privacy
Weihong Sheng, Jiajun Chen, Bin Cai, Chunqiang Hu, Meng Han, Jiguo Yu
https://arxiv.org/abs/2508.05518 https://

Local Distance Query with Differential Privacy
Differential Privacy (DP) is commonly employed to safeguard graph analysis or publishing. Distance, a critical factor in graph analysis, is typically handled using curator DP, where a trusted curator holds the complete neighbor lists of all vertices and answers queries privately. However, in many real-world scenarios, such a curator may not be present, posing a significant challenge for implementing differentially private distance queries under Local Differential Privacy (LDP). This paper propo…

Jemand möge den Autor dieses Artikels bitte rechts raus wirken. Er überschreitet die zulässige Floskel/Absatz bei Weitem.
Ach, 100 Jahre zu spät?
https://hwk1.hebis.de/zeitungen-hlbrm/periodical/pageview/1586173?query=Kaffee

Honestly, I don't want to take a PhD for every LLM query that random people make. It was very exhausting to do just one.

Learning Optimal Posted Prices for a Unit-Demand Buyer
Yifeng Teng, Yifan Wang
https://arxiv.org/abs/2506.02284 https://arxiv.org/pdf…

Learning Optimal Posted Prices for a Unit-Demand Buyer
We study the problem of learning the optimal item pricing for a unit-demand buyer with independent item values, and the learner has query access to the buyer's value distributions. We consider two common query models in the literature: the sample access model where the learner can obtain a sample of each item value, and the pricing query model where the learner can set a price for an item and obtain a binary signal on whether the sampled value of the item is greater than our proposed price. In …

FO-Query Enumeration over SLP-Compressed Structures of Bounded Degree
Markus Lohrey, Sebastian Maneth, Markus L. Schmid
https://arxiv.org/abs/2506.19421 ht…

FO-Query Enumeration over SLP-Compressed Structures of Bounded Degree
Enumerating the result set of a first-order query over a relational structure of bounded degree can be done with linear preprocessing and constant delay. In this work, we extend this result towards the compressed perspective where the structure is given in a potentially highly compressed form by a straight-line program (SLP). Our main result is an algorithm that enumerates the result set of a first-order query over a structure of bounded degree that is represented by an SLP satisfying the so-ca…

Efficient and Effective Query Context-Aware Learning-to-Rank Model for Sequential Recommendation
Andrii Dzhoha, Alisa Mironenko, Vladimir Vlasov, Maarten Versteegh, Marjan Celikik
https://arxiv.org/abs/2507.03789

Efficient and Effective Query Context-Aware Learning-to-Rank Model for Sequential Recommendation
Modern sequential recommender systems commonly use transformer-based models for next-item prediction. While these models demonstrate a strong balance between efficiency and quality, integrating interleaving features - such as the query context (e.g., browse category) under which next-item interactions occur - poses challenges. Effectively capturing query context is crucial for refining ranking relevance and enhancing user engagement, as it provides valuable signals about user intent within a se…

Bin ja sehr froh, diesen tollen Erklärartikel zu Excel Power Query gefunden zu haben, selbstreferenzierende Tabellen tun genau das, was ich heute für eine Auswertung von Daten gesucht habe. Von selbst wäre ich da wahrscheinlich nie drauf gekommen, habe aber auch nicht die Zeit (und Lust), mich noch intensiver mit Excel zu befassen.
Henne oder Ei: Selbstreferenzierende Tabellen in Power Query | Der Tabellenexperte

Complexity of learning matchings and half graphs via edge queries
Nikhil S. Mande, Swagato Sanyal, Viktor Zamaraev
https://arxiv.org/abs/2507.03151 https:/…

Complexity of learning matchings and half graphs via edge queries
The problem of learning or reconstructing an unknown graph from a known family via partial-information queries arises as a mathematical model in various contexts. The most basic type of access to the graph is via \emph{edge queries}, where an algorithm may query the presence/absence of an edge between a pair of vertices of its choosing, at unit cost. While more powerful query models have been extensively studied in the context of graph reconstruction, the basic model of edge queries seems to …

@… just URL query param slop 😅

https://mastodon.social/@shoppingtonz/114979972981864162
This is my post about (#)memes in (#)Wikidata and it links to a query and it got instructions how to "Run query".
Could be interesting for me to see the "structure" of memes...probably I…

As recently as last year I was recommending to my #Math students that if they were having trouble with an elementary algebra expression, they could try using the Google search bar to solve or simplify something. Maybe I should show them this instead.🤦

Dieser wurde 1931 in der Jägermais-Siedlung geschaffen: https://digital.wienbibliothek.at/wbrobv/periodical/pageview/1681036?query=hebenstreitplatz

Resolution Limits of Non-Adaptive 20 Questions Estimation for Tracking Multiple Moving Targets
Chunsong Sun, Lin Zhou, Jingjing Wang, Weijie Yuan, Chunxiao Jiang, Alfred Hero
https://arxiv.org/abs/2507.02274

Resolution Limits of Non-Adaptive 20 Questions Estimation for Tracking Multiple Moving Targets
Motivated by the practical application of beam tracking of multiple devices in Multiple Input Multiple Output (MIMO) communication, we study the problem of non-adaptive twenty questions estimation for locating and tracking multiple moving targets under a query-dependent noisy channel. Specifically, we derive a non-asymptotic bound and a second-order asymptotic bound on resolution for optimal query procedures and provide numerical examples to illustrate our results. In particular, we demonstrate…

systemd definitely does get many things right. My current favorite is how it sets the system resolver to loopback and provides an own DNS server.
Common Linux tradition was to tell processes to use getaddrinfo, where nsswitch then provides configurable backends. That means that every process goes through loading /etc/nsswitch.conf, but worse, it reduces DNS to a terrible subset. Query SVCB records? tough luck, you're on your own.

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[7/10]:
- Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs
Shaojie Zhang, Jiahui Yang, Jianqin Yin, Zhenbo Luo, Jian Luan

LLM4Hint: Leveraging Large Language Models for Hint Recommendation in Offline Query Optimization
Suchen Liu, Jun Gao, Yinjun Han, Yang Lin
https://arxiv.org/abs/2507.03384

LLM4Hint: Leveraging Large Language Models for Hint Recommendation in Offline Query Optimization
Query optimization is essential for efficient SQL query execution in DBMS, and remains attractive over time due to the growth of data volumes and advances in hardware. Existing traditional optimizers struggle with the cumbersome hand-tuning required for complex workloads, and the learning-based methods face limitations in ensuring generalization. With the great success of Large Language Model (LLM) across diverse downstream tasks, this paper explores how LLMs can be incorporated to enhance the …

CTR-Guided Generative Query Suggestion in Conversational Search
Erxue Min, Hsiu-Yuan Huang, Xihong Yang, Min Yang, Xin Jia, Yunfang Wu, Hengyi Cai, Junfeng Wang, Shuaiqiang Wang, Dawei Yin
https://arxiv.org/abs/2507.04072

CTR-Guided Generative Query Suggestion in Conversational Search
Generating effective query suggestions in conversational search requires aligning model outputs with user preferences, which is challenging due to sparse and noisy click signals. We propose GQS, a generative framework that integrates click modeling and preference optimization to enhance real-world user engagement. GQS consists of three key components: (1) a Multi-Source CTR Modeling module that captures diverse contextual signals to estimate fine-grained click-through rates; (2) a Diversity-Awa…

Optimizing Mesh to Improve the Triangular Expansion Algorithm for Computing Visibility Regions
Jan Mikula (Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague), Miroslav Kulich (Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague)

Optimizing Mesh to Improve the Triangular Expansion Algorithm for Computing Visibility Regions
This paper addresses the problem of improving the query performance of the triangular expansion algorithm (TEA) for computing visibility regions by finding the most advantageous instance of the triangular mesh, the preprocessing structure. The TEA recursively traverses the mesh while keeping track of the visible region, the set of all points visible from a query point in a polygonal world. We show that the measured query time is approximately proportional to the number of triangle edge expansio…

This https://arxiv.org/abs/2504.21398 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

In a Few Words: Comparing Weak Supervision and LLMs for Short Query Intent Classification
User intent classification is an important task in information retrieval. Previously, user intents were classified manually and automatically; the latter helped to avoid hand labelling of large datasets. Recent studies explored whether LLMs can reliably determine user intent. However, researchers have recognized the limitations of using generative LLMs for classification tasks. In this study, we empirically compare user intent classification into informational, navigational, and transactional c…

PrivTru: A Privacy-by-Design Data Trustee Minimizing Information Leakage
Lukas Gehring, Florian Tschorsch
https://arxiv.org/abs/2506.06124 https://

PrivTru: A Privacy-by-Design Data Trustee Minimizing Information Leakage
Data trustees serve as intermediaries that facilitate secure data sharing between independent parties. This paper offers a technical perspective on Data trustees, guided by privacy-by-design principles. We introduce PrivTru, an instantiation of a data trustee that provably achieves optimal privacy properties. Therefore, PrivTru calculates the minimal amount of information the data trustee needs to request from data sources to respond to a given query. Our analysis shows that PrivTru minimizes i…

Enhancing Customer Service Chatbots with Context-Aware NLU through Selective Attention and Multi-task Learning
Subhadip Nandi, Neeraj Agrawal, Anshika Singh, Priyanka Bhatt
https://arxiv.org/abs/2506.01781

Enhancing Customer Service Chatbots with Context-Aware NLU through Selective Attention and Multi-task Learning
Customer service chatbots are conversational systems aimed at addressing customer queries, often by directing them to automated workflows. A crucial aspect of this process is the classification of the customer's intent. Presently, most intent classification models for customer care utilise only customer query for intent prediction. This may result in low-accuracy models, which cannot handle ambiguous queries. An ambiguous query like "I didn't receive my package" could indicate a delayed order, …

Sensitivity and Query Complexity under Uncertainty
Deepu Benson, Balagopal Komarath, Nikhil Mande, Sai Soumya Nalli, Jayalal Sarma, Karteek Sreenivasaiah
https://arxiv.org/abs/2507.00148

Sensitivity and Query Complexity under Uncertainty
In this paper, we study the query complexity of Boolean functions in the presence of uncertainty, motivated by parallel computation with an unlimited number of processors where inputs are allowed to be unknown. We allow each query to produce three results: zero, one, or unknown. The output could also be: zero, one, or unknown, with the constraint that we should output ''unknown'' only when we cannot determine the answer from the revealed input bits. Such an extension of a Boolean function is ca…

Data-Aware Socratic Query Refinement in Database Systems
Ruiyuan Zhang, Chrysanthi Kosyfaki, Xiaofang Zhou
https://arxiv.org/abs/2508.05061 https://arxiv.o…

Data-Aware Socratic Query Refinement in Database Systems
In this paper, we propose Data-Aware Socratic Guidance (DASG), a dialogue-based query enhancement framework that embeds \linebreak interactive clarification as a first-class operator within database systems to resolve ambiguity in natural language queries. DASG treats dialogue as an optimization decision, asking clarifying questions only when the expected execution cost reduction exceeds the interaction overhead. The system quantifies ambiguity through linguistic fuzziness, schema grounding con…

Join Dennis Berger, Marco Petris, and Volker Carlguth to explore 'Intent-Based Clustering.' An approach to overcome some limitations of modern hybrid search systems. Discover how upfront LLM-supported in-depth query understanding can be applied in various steps, including retrieval, clustering, validation, and presentation. Learn about the process of moving from prototype to production for large-scale, high-volume e-commerce searches.

What you see is what you mean; intent based ecommerce search
In today's e-commerce landscape, hybrid search systems represent the market standard, yet they often struggle with highly inspirational queries, lack of precision in semantic recall, and presentation of diversity. Ambiguity in search terms can lead to disorganized results or overshadowed relevant products. This session will demonstrate how an upfront LLM-supported in depth query understanding can increase recall meaningfully without sacrificing precision. We show how LLM-driven query understand…

Measuring Hypothesis Testing Errors in the Evaluation of Retrieval Systems
Jack McKechnie, Graham McDonald, Craig Macdonald
https://arxiv.org/abs/2507.07924

Measuring Hypothesis Testing Errors in the Evaluation of Retrieval Systems
The evaluation of Information Retrieval (IR) systems typically uses query-document pairs with corresponding human-labelled relevance assessments (qrels). These qrels are used to determine if one system is better than another based on average retrieval performance. Acquiring large volumes of human relevance assessments is expensive. Therefore, more efficient relevance assessment approaches have been proposed, necessitating comparisons between qrels to ascertain their efficacy. Discriminative pow…

Graph theory-based automated quantum algorithm for efficient querying of acyclic and multiloop causal configurations
Salvador A. Ochoa-Oregon, Juan P. Uribe-Ram\'irez, Roger J. Hern\'andez-Pinto, Selomit Ram\'irez-Uribe, Germ\'an Rodrigo
https://arxiv.org/abs/2508.04019

Graph theory-based automated quantum algorithm for efficient querying of acyclic and multiloop causal configurations
Quantum algorithms provide a promising framework in high-energy physics, in particular, for unraveling the causal configurations of multiloop Feynman diagrams by identifying Feynman propagators with qubits, a challenge analogous to querying directed acyclic graphs in graph theory. In this paper, we present the Minimum Clique-optimised quantum Algorithm (MCA), an automated quantum algorithm designed to efficiently query the causal structures within the Loop-Tree Duality. The MCA quantum algorith…

This https://arxiv.org/abs/2503.18941 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Exploring Training and Inference Scaling Laws in Generative Retrieval
Generative retrieval reformulates retrieval as an autoregressive generation task, where large language models (LLMs) generate target documents directly from a query. As a novel paradigm, the mechanisms that underpin its performance and scalability remain largely unexplored. We systematically investigate training and inference scaling laws in generative retrieval, exploring how model size, training data scale, and inference-time compute jointly influence performance. We propose a novel evaluatio…

Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach
Yingze Li, Xianglong Liu, Dong Wang, Zixuan Wang, Hongzhi Wang, Kaixing Zhang, Yiming Guan
https://arxiv.org/abs/2507.07438

Algorithmic Complexity Attacks on All Learned Cardinality Estimators: A Data-centric Approach
Learned cardinality estimators show promise in query cardinality prediction, yet they universally exhibit fragility to training data drifts, posing risks for real-world deployment. This work is the first to theoretical investigate how minimal data-level drifts can maximally degrade the accuracy of learned estimators. We propose data-centric algorithmic complexity attacks against learned estimators in a black-box setting, proving that finding the optimal attack strategy is NP-Hard. To address th…

Boosting Temporal Sentence Grounding via Causal Inference
Kefan Tang, Lihuo He, Jisheng Dang, Xinbo Gao
https://arxiv.org/abs/2507.04958 https://

Boosting Temporal Sentence Grounding via Causal Inference
Temporal Sentence Grounding (TSG) aims to identify relevant moments in an untrimmed video that semantically correspond to a given textual query. Despite existing studies having made substantial progress, they often overlook the issue of spurious correlations between video and textual queries. These spurious correlations arise from two primary factors: (1) inherent biases in the textual data, such as frequent co-occurrences of specific verbs or phrases, and (2) the model's tendency to overfit to…

NAM: A Normalization Attention Model for Personalized Product Search In Fliggy
Shui Liu, Mingyuan Tao, Maofei Que, Pan Li, Dong Li, Shenghua Ni, Zhuoran Zhuang
https://arxiv.org/abs/2506.08382

NAM: A Normalization Attention Model for Personalized Product Search In Fliggy
Personalized product search provides significant benefits to e-commerce platforms by extracting more accurate user preferences from historical behaviors. Previous studies largely focused on the user factors when personalizing the search query, while ignoring the item perspective, which leads to the following two challenges that we summarize in this paper: First, previous approaches relying only on co-occurrence frequency tend to overestimate the conversion rates for popular items and underestim…

This https://arxiv.org/abs/2412.05561 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

Can the Rookies Cut the Tough Cookie? Exploring the Use of LLMs for SQL Equivalence Checking
Equivalence checking of SQL queries is an intractable problem often encountered in settings ranging from grading SQL submissions to debugging query optimizers. Despite recent work toward developing practical solutions, only simple queries written using a small subset of SQL are supported, leaving the equivalence checking of sophisticated SQL queries at the mercy of intensive, potentially error-prone, manual analysis. In this paper, we explore how LLMs can be used to reason with SQL queries to a…

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
Ziqi Miao, Lijun Li, Yuan Xiong, Zhenhua Liu, Pengyu Zhu, Jing Shao
https://arxiv.org/abs/2507.05248

Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can steer its subsequent behavior toward policy-violating content. Building on this insight, we propose Response Attack, which uses an auxiliary LLM to generate a mildly harmful response to a paraphrased version of the original malicious query. They are then form…

Replaced article(s) found for cs.DB. https://arxiv.org/list/cs.DB/new/
[1/1]:
Query Rewriting via LLMs
https://arxiv.org/abs/2…

This https://arxiv.org/abs/2502.06200 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…

On the query complexity of sampling from non-log-concave distributions
We study the problem of sampling from a $d$-dimensional distribution with density $p(x)\propto e^{-f(x)}$, which does not necessarily satisfy good isoperimetric conditions. Specifically, we show that for any $L,M$ satisfying $LM\ge d\ge 5$, $ε\in \left(0,\frac{1}{32}\right)$, and any algorithm with query accesses to the value of $f(x)$ and $\nabla f(x)$, there exists an $L$-log-smooth distribution with second moment at most $M$ such that the algorithm requires $\left(\frac{LM}{dε}\right)^{�…

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
Wei Chow, Yuan Gao, Linfeng Li, Xian Wang, Qi Xu, Hang Song, Lingdong Kong, Ran Zhou, Yi Zeng, Yidong Cai, Botian Jiang, Shilin Xu, Jiajun Zhang, Minghui Qiu, Xiangtai Li, Tianshu Yang, Siliang Tang, Juncheng Li
https://arxiv.org/abs/2506.03144

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
Semantic retrieval is crucial for modern applications yet remains underexplored in current research. Existing datasets are limited to single languages, single images, or singular retrieval conditions, often failing to fully exploit the expressive capacity of visual information as evidenced by maintained performance when images are replaced with captions. However, practical retrieval scenarios frequently involve interleaved multi-condition queries with multiple images. Hence, this paper introduc…

Query Attribute Modeling: Improving search relevance with Semantic Search and Meta Data Filtering
Karthik Menon, Batool Arhamna Haider, Muhammad Arham, Kanwal Mehreen, Ram Mohan Rao Kadiyala, Hamza Farooq
https://arxiv.org/abs/2508.04683

Query Attribute Modeling: Improving search relevance with Semantic Search and Meta Data Filtering
This study introduces Query Attribute Modeling (QAM), a hybrid framework that enhances search precision and relevance by decomposing open text queries into structured metadata tags and semantic elements. QAM addresses traditional search limitations by automatically extracting metadata filters from free-form text queries, reducing noise and enabling focused retrieval of relevant items. Experimental evaluation using the Amazon Toys Reviews dataset (10,000 unique items with 40,000+ reviews and d…

Replaced article(s) found for cs.DB. https://arxiv.org/list/cs.DB/new
[1/1]:
- QUITE: A Query Rewrite System Beyond Rules with LLM Agents
Yuyang Song, Hanxu Yan, Jiale Lao, Yibo Wang, Yufei Li, Yuanchun Zhou, Jianguo Wang, Mingjie Tang

Beyond Natural Language Plans: Structure-Aware Planning for Query-Focused Table Summarization
Weijia Zhang, Songgaojun Deng, Evangelos Kanoulas
https://arxiv.org/abs/2507.22829 …

Beyond Natural Language Plans: Structure-Aware Planning for Query-Focused Table Summarization
Query-focused table summarization requires complex reasoning, often approached through step-by-step natural language (NL) plans. However, NL plans are inherently ambiguous and lack structure, limiting their conversion into executable programs like SQL and hindering scalability, especially for multi-table tasks. To address this, we propose a paradigm shift to structured representations. We introduce a new structured plan, TaSoF, inspired by formalism in traditional multi-agent systems, and a fra…

Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
Sayyed Farid Ahamed, Sandip Roy, Soumya Banerjee, Marc Vucovich, Kevin Choi, Abdul Rahman, Alison Hu, Edward Bowen, Sachin Shetty
https://arxiv.org/abs/2505.23791

Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extraction (ME) attacks pose a significant risk to Machine Learning as a Service (MLaaS) platforms, enabling attackers to replicate confidential models by querying black-box (without internal insight) APIs. Despite FL's privacy-preserving goals, its distributed nature makes it particularly susceptible to such attacks. This p…

Cut-Query Algorithms with Few Rounds
Yotam Kenneth-Mordoch, Robert Krauthgamer
https://arxiv.org/abs/2506.20412 https://arxiv.org/pdf…

Cut-Query Algorithms with Few Rounds
In the cut-query model, the algorithm can access the input graph $G=(V,E)$ only via cut queries that report, given a set $S\subseteq V$, the total weight of edges crossing the cut between $S$ and $V\setminus S$. This model was introduced by Rubinstein, Schramm and Weinberg [ITCS'18] and its investigation has so far focused on the number of queries needed to solve optimization problems, such as global minimum cut. We turn attention to the round complexity of cut-query algorithms, and show that s…

PCPP-Based Reconfiguration Inapproximability: Query Complexity vs. Soundness Gap Trade-offs
Venkatesan Guruswami, Xuandi Ren, Kewen Wu
https://arxiv.org/abs/2507.01192

PCPP-Based Reconfiguration Inapproximability: Query Complexity vs. Soundness Gap Trade-offs
The Reconfiguration Inapproximability Hypothesis (RIH), recently established by Hirahara-Ohsaka (STOC'24) and Karthik-Manurangsi (ECCC'24), studies the hardness of reconfiguring one solution into another in constraint satisfaction problems (CSP) when restricted to approximate intermediate solutions. In this work, we make a tighter connection between RIH's soundness gap and that of probabilistically checkable proofs of proximity (PCPP). Consequently, we achieve an improved trade-off between soun…

GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval
Lingyuan Liu, Mengxiang Zhang
https://arxiv.org/abs/2506.04762

GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval
Large language models (LLMs)-based query expansion for information retrieval augments queries with generated hypothetical documents with LLMs. However, its performance relies heavily on the scale of the language models (LMs), necessitating larger, more advanced LLMs. This approach is costly, computationally intensive, and often has limited accessibility. To address these limitations, we introduce GOLFer - Smaller LMs-Generated Documents Hallucination Filter & Combiner - a novel method leveragin…

Lightweight Transformers for Zero-Shot and Fine-Tuned Text-to-SQL Generation Using Spider
Chirag Seth, Utkarsh Singh
https://arxiv.org/abs/2508.04623 https://

Lightweight Transformers for Zero-Shot and Fine-Tuned Text-to-SQL Generation Using Spider
Text-to-SQL translation enables non-expert users to query relational databases using natural language, with applications in education and business intelligence. This study evaluates three lightweight transformer models - T5-Small, BART-Small, and GPT-2 - on the Spider dataset, focusing on low-resource settings. We developed a reusable, model-agnostic pipeline that tailors schema formatting to each model's architecture, training them across 1000 to 5000 iterations and evaluating on 1000 test sam…

LIMAO: A Framework for Lifelong Modular Learned Query Optimization
Qihan Zhang, Shaolin Xie, Ibrahim Sabek
https://arxiv.org/abs/2507.00188 https://…

LIMAO: A Framework for Lifelong Modular Learned Query Optimization
Query optimizers are crucial for the performance of database systems. Recently, many learned query optimizers (LQOs) have demonstrated significant performance improvements over traditional optimizers. However, most of them operate under a limited assumption: a static query environment. This limitation prevents them from effectively handling complex, dynamic query environments in real-world scenarios. Extensive retraining can lead to the well-known catastrophic forgetting problem, which reduces …

Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion
Lingyuan Liu, Mengxiang Zhang
https://arxiv.org/abs/2506.04760

Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion
Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion, thereby enhancing information retrieval performance. However, the efficacy of this method is highly dependent on the quality of the generated documents, which often requires complex prompt strategies and the integration of advanced dense retrieval techniques. This can be both costly and computationally intensive. To mitigate these limitations, we explore the use of zero-shot LLM-based que…

On the Complexity of Knapsack under Explorable Uncertainty: Hardness and Algorithms
Jens Schl\"oter
https://arxiv.org/abs/2507.02657 https://

On the Complexity of Knapsack under Explorable Uncertainty: Hardness and Algorithms
In the knapsack problem under explorable uncertainty, we are given a knapsack instance with uncertain item profits. Instead of having access to the precise profits, we are only given uncertainty intervals that are guaranteed to contain the corresponding profits. The actual item profit can be obtained via a query. The goal of the problem is to adaptively query item profits until the revealed information suffices to compute an optimal (or approximate) solution to the underlying knapsack instance.…

Learned Adaptive Indexing
Suvam Kumar Das, Suprio Ray
https://arxiv.org/abs/2508.03471 https://arxiv.org/pdf/2508.03471

Learned Adaptive Indexing
Indexes can significantly improve search performance in relational databases. However, if the query workload changes frequently or new data updates occur continuously, it may not be worthwhile to build a conventional index upfront for query processing. Adaptive indexing is a technique in which an index gets built on the fly as a byproduct of query processing. In recent years, research in database indexing has taken a new direction where machine learning models are employed for the purpose of in…

Quantifying Query Fairness Under Unawareness
Thomas Jaenich, Alejandro Moreo, Alessandro Fabris, Graham McDonald, Andrea Esuli, Iadh Ounis, Fabrizio Sebastiani
https://arxiv.org/abs/2506.04140

Quantifying Query Fairness Under Unawareness
Traditional ranking algorithms are designed to retrieve the most relevant items for a user's query, but they often inherit biases from data that can unfairly disadvantage vulnerable groups. Fairness in information access systems (IAS) is typically assessed by comparing the distribution of groups in a ranking to a target distribution, such as the overall group distribution in the dataset. These fairness metrics depend on knowing the true group labels for each item. However, when groups are defin…

Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation
Y. Du
https://arxiv.org/abs/2507.05933 https:…

Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation
Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization robustness and neighborhood density metrics. Our approach is motivated by the observation that high-quality embeddings occupy geometrically stable regions in the embedding space and exhibit consistent neighborhood structures. We evaluate our method on 4 standar…

PLACE: Prompt Learning for Attributed Community Search
Shuheng Fang, Kangfei Zhao, Rener Zhang, Yu Rong, Jeffrey Xu Yu
https://arxiv.org/abs/2507.05311 htt…

PLACE: Prompt Learning for Attributed Community Search
In this paper, we propose PLACE (Prompt Learning for Attributed Community Search), an innovative graph prompt learning framework for ACS. Enlightened by prompt-tuning in Natural Language Processing (NLP), where learnable prompt tokens are inserted to contextualize NLP queries, PLACE integrates structural and learnable prompt tokens into the graph as a query-dependent refinement mechanism, forming a prompt-augmented graph. Within this prompt-augmented graph structure, the learned prompt tokens s…

Towards Serverless Processing of Spatiotemporal Big Data Queries
Diana Baumann, Tim C. Rese, David Bermbach
https://arxiv.org/abs/2507.06005 https://

Towards Serverless Processing of Spatiotemporal Big Data Queries
Spatiotemporal data are being produced in continuously growing volumes by a variety of data sources and a variety of application fields rely on rapid analysis of such data. Existing systems such as PostGIS or MobilityDB usually build on relational database systems, thus, inheriting their scale-out characteristics. As a consequence, big spatiotemporal data scenarios still have limited support even though many query types can easily be parallelized. In this paper, we propose our vision of a nativ…

On the Costs and Benefits of Learned Indexing for Dynamic High-Dimensional Data: Extended Version
Ter\'ezia Slanin\'akov\'a, Jaroslav Olha, David Proch\'azka, Matej Antol, Vlastislav Dohnal
https://arxiv.org/abs/2507.05865

On the Costs and Benefits of Learned Indexing for Dynamic High-Dimensional Data: Extended Version
One of the main challenges within the growing research area of learned indexing is the lack of adaptability to dynamically expanding datasets. This paper explores the dynamization of a static learned index for complex data through operations such as node splitting and broadening, enabling efficient adaptation to new data. Furthermore, we evaluate the trade-offs between static and dynamic approaches by introducing an amortized cost model to assess query performance in tandem with the build costs…

This https://arxiv.org/abs/2503.07219 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

Bag Semantics Query Containment: The CQ vs. UCQ Case and Other Stories
Query Containment Problem (QCP) is a fundamental decision problem in query processing and optimization. While QCP has for a long time been completely understood for the case of set semantics, decidability of QCP for conjunctive queries under multi-set semantics ($QCP_{\text{CQ}}^{\text{bag}}$) remains one of the most intriguing open problems in database theory. Certain effort has been put, in last 30 years, to solve this problem and some decidable special cases of $QCP_{\text{CQ}}^{\text{bag}}$…

KBest: Efficient Vector Search on Kunpeng CPU
Kaihao MA, Meiling Wang, Senkevich Oleg, Zijian LI, Daihao Xue, Dmitriy Malyshev, Yangming Lv, Shihai Xiao, Xiao Yan, Radionov Alexander, Weidi Zeng, Yuanzhan Gao, Zhiyu Zou, Yao xin, Liu Lin, Junhao Wu, Yiding Liu, Yaoyao Fu, Gongyi Wang, Gong Zhang, Fei Yi, Yingfan Liu
https://arxiv.org/abs/2…

KBest: Efficient Vector Search on Kunpeng CPU
Vector search, which returns the vectors most similar to a given query vector from a large vector dataset, underlies many important applications such as search, recommendation, and LLMs. To be economic, vector search needs to be efficient to reduce the resources required by a given query workload. However, existing vector search libraries (e.g., Faiss and DiskANN) are optimized for x86 CPU architectures (i.e., Intel and AMD CPUs) while Huawei Kunpeng CPUs are based on the ARM architecture and c…

Intent-Aware Neural Query Reformulation for Behavior-Aligned Product Search
Jayanth Yetukuri, Ishita Khan
https://arxiv.org/abs/2507.22213 https://arxiv.or…

Intent-Aware Neural Query Reformulation for Behavior-Aligned Product Search
Understanding and modeling buyer intent is a foundational challenge in optimizing search query reformulation within the dynamic landscape of e-commerce search systems. This work introduces a robust data pipeline designed to mine and analyze large-scale buyer query logs, with a focus on extracting fine-grained intent signals from both explicit interactions and implicit behavioral cues. Leveraging advanced sequence mining techniques and supervised learning models, the pipeline systematically capt…

Zero-Knowledge Verifiable Graph Query Evaluation via Expansion-Centric Operator Decomposition
Hao Wu, Changzheng Wei, Yanhao Wang, Li Lin, Yilong Leng, Shiyu He, Minghao Zhao, Hanghang Wu, Ying Yan, Aoying Zhou
https://arxiv.org/abs/2507.00427

Zero-Knowledge Verifiable Graph Query Evaluation via Expansion-Centric Operator Decomposition
This paper investigates the feasibility of achieving zero-knowledge verifiability for graph databases, enabling database owners to cryptographically prove the query execution correctness without disclosing the underlying data. Although similar capabilities have been explored for relational databases, their implementation for graph databases presents unique challenges. This is mainly attributed to the relatively large complexity of queries in graph databases. When translating graph queries into …

Query, Don't Train: Privacy-Preserving Tabular Prediction from EHR Data via SQL Queries
Josefa Lia Stoisser, Marc Boubnovski Martell, Kaspar M\"artens, Lawrence Phillips, Stephen Michael Town, Rory Donovan-Maiye, Julien Fauqueur
https://arxiv.org/abs/2505.21801

Query, Don't Train: Privacy-Preserving Tabular Prediction from EHR Data via SQL Queries
Electronic health records (EHRs) contain richly structured, longitudinal data essential for predictive modeling, yet stringent privacy regulations (e.g., HIPAA, GDPR) often restrict access to individual-level records. We introduce Query, Don't Train (QDT): a structured-data foundation-model interface enabling tabular inference via LLM-generated SQL over EHRs. Instead of training on or accessing individual-level examples, QDT uses a large language model (LLM) as a schema-aware query planner to g…

Function-based Labels for Complementary Recommendation: Definition, Annotation, and LLM-as-a-Judge
Chihiro Yamasaki, Kai Sugahara, Yuma Nagi, Kazushi Okamoto
https://arxiv.org/abs/2507.03945

Function-based Labels for Complementary Recommendation: Definition, Annotation, and LLM-as-a-Judge
Complementary recommendations enhance the user experience by suggesting items that are frequently purchased together while serving different functions from the query item. Inferring or evaluating whether two items have a complementary relationship requires complementary relationship labels; however, defining these labels is challenging because of the inherent ambiguity of such relationships. Complementary labels based on user historical behavior logs attempt to capture these relationships, but …

The Case for Instance-Optimized LLMs in OLAP Databases
Bardia Mohammadi, Laurent Bindschaedler
https://arxiv.org/abs/2507.04967 https://

The Case for Instance-Optimized LLMs in OLAP Databases
Large Language Models (LLMs) can enhance analytics systems with powerful data summarization, cleaning, and semantic transformation capabilities. However, deploying LLMs at scale -- processing millions to billions of rows -- remains prohibitively expensive in computation and memory. We present IOLM-DB, a novel system that makes LLM-enhanced database queries practical through query-specific model optimization. Instead of using general-purpose LLMs, IOLM-DB generates lightweight, specialized model…

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
Dipam Goswami, Liying Wang, Bart{\l}omiej Twardowski, Joost van de Weijer
https://arxiv.org/abs/2506.00037

Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models
Text embedding models enable semantic search, powering several NLP applications like Retrieval Augmented Generation by efficient information retrieval (IR). However, text embedding models are commonly studied in scenarios where the training data is static, thus limiting its applications to dynamic scenarios where new training data emerges over time. IR methods generally encode a huge corpus of documents to low-dimensional embeddings and store them in a database index. During retrieval, a semant…

A Learned Cost Model-based Cross-engine Optimizer for SQL Workloads
Andr\'as Strausz, Niels Pardon, Ioana Giurgiu
https://arxiv.org/abs/2506.02802 http…

A Learned Cost Model-based Cross-engine Optimizer for SQL Workloads
Lakehouse systems enable the same data to be queried with multiple execution engines. However, selecting the engine best suited to run a SQL query still requires a priori knowledge of the query computational requirements and an engine capability, a complex and manual task that only becomes more difficult with the emergence of new engines and workloads. In this paper, we address this limitation by proposing a cross-engine optimizer that can automate engine selection for diverse SQL queries throu…

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
Jang-Hyun Kim, Jinuk Kim, Sangwoo Kwon, Jae W. Lee, Sangdoo Yun, Hyun Oh Song
https://arxiv.org/abs/2505.23416

KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
Transformer-based large language models (LLMs) cache context as key-value (KV) pairs during inference. As context length grows, KV cache sizes expand, leading to substantial memory overhead and increased attention latency. This paper introduces KVzip, a query-agnostic KV cache eviction method enabling effective reuse of compressed KV caches across diverse queries. KVzip quantifies the importance of a KV pair using the underlying LLM to reconstruct original contexts from cached KV pairs, subsequ…

This https://arxiv.org/abs/2505.19189 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval
Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing query decomposition for MVR performance is not end-to-end differentiable. Even worse, jointly solving this problem and training the downstream retrieval-based systems, say RAG systems could be highly inefficient. To overcome these challenges, we propose Performa…

TailorSQL: An NL2SQL System Tailored to Your Query Workload
Kapil Vaidya, Jialin Ding, Sebastian Kosak, David Kernert, Chuan Lei, Xiao Qin, Abhinav Tripathy, Ramesh Balan, Balakrishnan Narayanaswamy, Tim Kraska
https://arxiv.org/abs/2505.23039

TailorSQL: An NL2SQL System Tailored to Your Query Workload
NL2SQL (natural language to SQL) translates natural language questions into SQL queries, thereby making structured data accessible to non-technical users, serving as the foundation for intelligent data applications. State-of-the-art NL2SQL techniques typically perform translation by retrieving database-specific information, such as the database schema, and invoking a pre-trained large language model (LLM) using the question and retrieved information to generate the SQL query. However, existin…