Tootfinder

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…

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, …

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…

This https://arxiv.org/abs/2505.24226 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

E^2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness
Graph-based RAG methods like GraphRAG have shown promising global understanding of the knowledge base by constructing hierarchical entity graphs. However, they often suffer from inefficiency and rely on manually pre-defined query modes, limiting practical use. In this paper, we propose E^2GraphRAG, a streamlined graph-based RAG framework that improves both Efficiency and Effectiveness. During the indexing stage, E^2GraphRAG constructs a summary tree with large language models and an entity grap…

Soul Vlog posts sorted by relevance for query "Grateful Dead".
Sorted by date
https://soulvlog.blogspot.com/search?q=Grateful Dead&m=1

Folks familiar with Xilinx FPGA minutiae (i.e. @… probably): is there a register I can query via the ICAP that lets me determine how the current bitstream was loaded?
In other words, can I distinguish the same bitstream loaded via x1 SPI vs x4 SPI vs JTAG once the configuration has completed?

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…

Done mapping all 10 #barangays of Hadji Muhtamad, Basilan, #Philippines 🇵🇭 in #OpenStreetMap, creating their #Wikidata

Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Large Language Models
Philip Quirke, Narmeen Oozeer, Chaithanya Bandi, Amir Abdullah, Jason Hoelscher-Obermaier, Jeff M. Phillips, Joshua Greaves, Clement Neo, Fazl Barez, Shriyash Upadhyay
https://arxiv.org/abs/2506.00051

Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Large Language Models
This position paper argues that the prevailing trajectory toward ever larger, more expensive generalist foundation models controlled by a handful of big companies limits innovation and constrains progress. We challenge this approach by advocating for an "Expert Orchestration" framework as a superior alternative that democratizes LLM advancement. Our proposed framework intelligently selects from thousands of existing models based on query requirements and decomposition, focusing on identifying w…

SSCard: Substring Cardinality Estimation using Suffix Tree-Guided Learned FM-Index
Yirui Zhan, Wen Nie, Jun Gao
https://arxiv.org/abs/2505.24312 https://…

SSCard: Substring Cardinality Estimation using Suffix Tree-Guided Learned FM-Index
Accurate cardinality estimation of substring queries, which are commonly expressed using the SQL LIKE predicate, is crucial for query optimization in database systems. While both rule-based methods and machine learning-based methods have been developed to optimize various aspects of cardinality estimation, their absence of error bounds may result in substantial estimation errors, leading to suboptimal execution plans. In this paper, we propose SSCard, a novel SubString Cardinality estimator tha…

This https://arxiv.org/abs/2505.12304 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSI_…

Pre-trained Prompt-driven Community Search
The "pre-train, prompt" paradigm is widely adopted in various graph-based tasks and has shown promising performance in community detection. Most existing semi-supervised community detection algorithms detect communities based on known ones, and the detected communities typically do not contain the given query node. Therefore, they are not suitable for searching the community of a given node. Motivated by this, we adopt this paradigm into the semi-supervised community search for the first time a…

Small Stickers, Big Meanings: A Multilingual Sticker Semantic Understanding Dataset with a Gamified Approach
Heng Er Metilda Chee, Jiayin Wang, Zhiqiang Guo, Weizhi Ma, Min Zhang
https://arxiv.org/abs/2506.01668

Small Stickers, Big Meanings: A Multilingual Sticker Semantic Understanding Dataset with a Gamified Approach
Stickers, though small, are a highly condensed form of visual expression, ubiquitous across messaging platforms and embraced by diverse cultures, genders, and age groups. Despite their popularity, sticker retrieval remains an underexplored task due to the significant human effort and subjectivity involved in constructing high-quality sticker query datasets. Although large language models (LLMs) excel at general NLP tasks, they falter when confronted with the nuanced, intangible, and highly spec…

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…

I built a Firefox extension that allows you to append arbitrary arguments/text to each Google query automatically. I will now go through whatever hell is required to get it onto the addon store. It's up on GitHub for the curious. https://github.com/theodric/ArgsGoogleSearches

An Adversary-Resistant Multi-Agent LLM System via Credibility Scoring
Sana Ebrahimi, Mohsen Dehghankar, Abolfazl Asudeh
https://arxiv.org/abs/2505.24239 ht…

An Adversary-Resistant Multi-Agent LLM System via Credibility Scoring
While multi-agent LLM systems show strong capabilities in various domains, they are highly vulnerable to adversarial and low-performing agents. To resolve this issue, in this paper, we introduce a general and adversary-resistant multi-agent LLM framework based on credibility scoring. We model the collaborative query-answering process as an iterative game, where the agents communicate and contribute to a final system output. Our system associates a credibility score that is used when aggregating…

This https://arxiv.org/abs/2501.02772 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

GeAR: Generation Augmented Retrieval
Document retrieval techniques are essential for developing large-scale information systems. The common approach involves using a bi-encoder to compute the semantic similarity between a query and documents. However, the scalar similarity often fail to reflect enough information, hindering the interpretation of retrieval results. In addition, this process primarily focuses on global semantics, overlooking the finer-grained semantic relationships between the query and the document's content. In th…

This https://arxiv.org/abs/2409.17275 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
Retrieval-Augmented Generation (RAG) has been empirically shown to enhance the performance of large language models (LLMs) in knowledge-intensive domains such as healthcare, finance, and legal contexts. Given a query, RAG retrieves relevant documents from a corpus and integrates them into the LLMs' generation process. In this study, we investigate the adversarial robustness of RAG, focusing specifically on examining the retrieval system. First, across 225 different setup combinations of corpus,…

Survey: Graph Databases
Miguel E. Coimbra, Lucie Svit\'akov\'a, Alexandre P. Francisco, Lu\'is Veiga
https://arxiv.org/abs/2505.24758 https://

Survey: Graph Databases
Graph databases have become essential tools for managing complex and interconnected data, which is common in areas like social networks, bioinformatics, and recommendation systems. Unlike traditional relational databases, graph databases offer a more natural way to model and query intricate relationships, making them particularly effective for applications that demand flexibility and efficiency in handling interconnected data. Despite their increasing use, graph databases face notable challen…

Azure Database for PostgreSQL Blog author and Microsoft employee "JoshMSFT" shares details on Microsoft's new PostgreSQL extension for Visual Studio Code.
Feature set includes:
1. Schema Visualization
2. Database aware GitHub Copilot
3. Database Explorer
4. Query History
5. Query Editing with Context-aware IntelliSense
 
"Announcing a new IDE for PostgreSQL in VS Code from Microsoft"

This https://arxiv.org/abs/2505.07155 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Reassessing Large Language Model Boolean Query Generation for Systematic Reviews
Systematic reviews are comprehensive literature reviews that address highly focused research questions and represent the highest form of evidence in medicine. A critical step in this process is the development of complex Boolean queries to retrieve relevant literature. Given the difficulty of manually constructing these queries, recent efforts have explored Large Language Models (LLMs) to assist in their formulation. One of the first studies,Wang et al., investigated ChatGPT for this task, foll…

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…

Whoever greenlit this _focus-stealing_ nag on the #Google home page, where it routinely interrupts whatever I'm typing into the search box: know that you're helping to drive me _away_ from Google, and that I hope you develop some sort of horrific incurable body odor to which your own nose never becomes acclimated.

MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction
Yunkee Chae, Kyogu Lee
https://arxiv.org/abs/2505.23305 https://

MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction
We present MGE-LDM, a unified latent diffusion framework for simultaneous music generation, source imputation, and query-driven source separation. Unlike prior approaches constrained to fixed instrument classes, MGE-LDM learns a joint distribution over full mixtures, submixtures, and individual stems within a single compact latent diffusion model. At inference, MGE-LDM enables (1) complete mixture generation, (2) partial generation (i.e., source imputation), and (3) text-conditioned extraction …

This https://arxiv.org/abs/2504.08756 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation
Existing RAG benchmarks often overlook query difficulty, leading to inflated performance on simpler questions and unreliable evaluations. A robust benchmark dataset must satisfy three key criteria: quality, diversity, and difficulty, which capturing the complexity of reasoning based on hops and the distribution of supporting evidence. In this paper, we propose MHTS (Multi-Hop Tree Structure), a novel dataset synthesis framework that systematically controls multi-hop reasoning complexity by leve…

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…

#Python Friday #273: Query Excel Files With #DuckDB
https://pythonfriday.dev/2025/04/273-q

#273: Query Excel Files With DuckDB - Python Friday
None

Idly wondered if there are any carolean post boxes, and a search of OSM suggests there's at least eight.
https://overpass-turbo.eu/s/24R8

This https://arxiv.org/abs/2412.00639 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries
Multi-modal datasets, like those involving images, often miss the detailed descriptions that properly capture the rich information encoded in each item. This makes answering complex natural language queries a major challenge in this domain. In particular, unlike the traditional nearest neighbor search, where the tuples and the query are represented as points in a single metric space, these settings involve queries and tuples embedded in fundamentally different spaces, making the traditional que…

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…

Modern applications require search capabilities that go beyond basic text matching. They must be fast, accurate, personalised and context-aware. At this year's Berlin Buzzwords, Saurabh Singh will demonstrate how OpenSearch’s latest AI/ML enhancements and engine improvements enable organisations to build intelligent, scalable search experiences that meet these evolving needs.
Learn more:

From Search to Insight: Leveraging OpenSearch for Scalable, AI-Driven Search Experiences
Observability, log analytics, GenAI systems, and RAG pipelines must query massive volumes of semantic embeddings to retrieve relevant content instantly. Today’s search systems often fall short in handling high-dimensional vector data and similarity search. OpenSearch 3.0 brings significant architectural improvements to address these challenges. Integrating Apache Lucene 10 and JVM 21, the platform delivers 20% faster queries than its 2.x predecessor and 10× the throughput of 1.x versions. Ne…

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
Krishna Acharya, Aleksandr V. Petrov, Juba Ziani
https://arxiv.org/abs/2506.01910

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation
We propose Generative Low-rank language model with Semantic Search (GLoSS), a generative recommendation framework that combines large language models with dense retrieval for sequential recommendation. Unlike prior methods such as GPT4Rec, which rely on lexical matching via BM25, GLoSS uses semantic search to retrieve relevant items beyond lexical matching. For query generation, we employ 4-bit quantized LlaMA-3 models fine-tuned with low-rank adaptation (LoRA), enabling efficient training and …

@… how can I customize search engines in Vivaldi on Android? I don't only want to select from a predefined list, I want to customize the search query string with my own options.

This https://arxiv.org/abs/2505.21801 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

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…

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
Seongwan Park, Taeklim Kim, Youngjoong Ko
https://arxiv.org/abs/2506.00041

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval
Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously uninterpretable dense embeddings from DPR models into distinct, interpretable latent concepts. We generate natural language descriptions for each latent concept, enabling human interpretations of both the dense embeddings and the query-document similarity scores…

Various Artists – 2000’s Horrors
#byncnd

This https://arxiv.org/abs/2411.06426 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains
As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous jailbreak attacks have been proposed to assess the security defense of LLMs. Current jailbreak attacks mainly rely on scenario camouflage, prompt obfuscation, prompt optimization, and prompt iterative optimization to conceal malicious prompts. In particular, sequential prompt chains in a single query can lead LLMs to …

Today I had a 1h meeting followed by 2h of code reading and DB forensics which resulted in a rather simple SQL query that, when run daily via cron, should remove the need for a manual step that an operator had to do regularily (and maybe did not do properly, but instread wasted an hour on dumb clicking instead).

This https://arxiv.org/abs/2503.23776 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

VIDEX: A Disaggregated and Extensible Virtual Index for the Cloud and AI Era
Virtual index, also known as hypothetical indexes, play a crucial role in database query optimization. However, with the rapid advancement of cloud computing and AI-driven models for database optimization, traditional virtual index approaches face significant challenges. Cloud-native environments often prohibit direct conducting query optimization process on production databases due to stability requirements and data privacy concerns. Moreover, while AI models show promising progress, their int…

This https://arxiv.org/abs/2502.17057 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance
Large language models (LLMs) have demonstrated significant potential in enhancing dense retrieval through query augmentation. However, most existing methods treat the LLM and the retriever as separate modules, overlooking the alignment between generation and ranking objectives. In this work, we propose ExpandR, a unified LLM-augmented dense retrieval framework that jointly optimizes both the LLM and the retriever. ExpandR employs the LLM to generate semantically rich query expansions, which are…

I feel like ChatGPT is taking a jab at other types of models here.

This https://arxiv.org/abs/2504.11540 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

Pruning in Snowflake: Working Smarter, Not Harder
Modern cloud-based data analytics systems must efficiently process petabytes of data residing on cloud storage. A key optimization technique in state-of-the-art systems like Snowflake is partition pruning - skipping chunks of data that do not contain relevant information for computing query results. While partition pruning based on query predicates is a well-established technique, we present new pruning techniques that extend the scope of partition pruning to LIMIT, top-k, and JOIN operations…

LINEAGEX: A Column Lineage Extraction System for SQL
Shi Heng Zhang, Zhengjie Miao, Jiannan Wang
https://arxiv.org/abs/2505.23133 https://

LINEAGEX: A Column Lineage Extraction System for SQL
As enterprise data grows in size and complexity, column-level data lineage, which records the creation, transformation, and reference of each column in the warehouse, has been the key to effective data governance that assists tasks like data quality monitoring, storage refactoring, and workflow migration. Unfortunately, existing systems introduce overheads by integration with query execution or fail to achieve satisfying accuracy for column lineage. In this paper, we demonstrate LINEAGEX, a lig…

This https://arxiv.org/abs/2505.19164 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

BroadGen: A Framework for Generating Effective and Efficient Advertiser Broad Match Keyphrase Recommendations
In the domain of sponsored search advertising, the focus of Keyphrase recommendation has largely been on exact match types, which pose issues such as high management expenses, limited targeting scope, and evolving search query patterns. Alternatives like Broad match types can alleviate certain drawbacks of exact matches but present challenges like poor targeting accuracy and minimal supervisory signals owing to limited advertiser usage. This research defines the criteria for an ideal broad matc…

Join Kevin Liang at this year's Berlin Buzzwords, where he will discuss how Apache Solr/Lucene builds dense vector indexes and talk about how he and his team optimised their dense vector setup, sharing the challenges they faced and the best practices they learned along the way.
Learn more: https…

This https://arxiv.org/abs/2505.22299 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queries
Information retrieval plays a crucial role in resource localization. Current dense retrievers retrieve the relevant documents within a corpus via embedding similarities, which compute similarities between dense vectors mainly depending on word co-occurrence between queries and documents, but overlook the real query intents. Thus, they often retrieve numerous irrelevant documents. Particularly in the scenarios of complex queries such as \emph{negative-constraint queries}, their retrieval perfo…

This https://arxiv.org/abs/2502.14350 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

Optimize Cardinality Estimation Model Pretraining by Simplifying the Training Datasets
The cardinality estimation is a key aspect of query optimization research, and its performance has significantly improved with the integration of machine learning. To overcome the "cold start" problem or the lack of model transferability in learned cardinality estimators, some pre-training cardinality estimation models have been proposed that use learning across multiple datasets and corresponding workloads. These models typically train on a dataset created by uniformly sampling from many datas…