arXiv subjects

Nick Koudas

Publications and source records attributed to Nick Koudas.

At least 19 recordsLinked to original sources

arXiv2026

HNSW with Accuracy Guarantees Using Graph Spanners

Hierarchical Navigable Small World (HNSW) graphs serve as the industry standard due to their logarithmic complexity and strong empirical performance. However, HNSW relies on greedy graph traversal, a heuristic that provides no theoretical guarantees of correctness. In this paper, we propose a novel "Certify-then-Rectify" framework that bridges the gap between the speed of heuristic search and the rigor of exact retrieval. Rather than discarding HNSW, our approach first employs a distribution-free statistical certifier to dynamically evaluate the quality of a standard HNSW search with minimal overhead. If certification indicates that the retrieved neighbors are of low quality, the framework safely escalates to a rigorous exact recovery algorithm. To make this exact recovery computationally feasible, we reinterpret the HNSW graph as a geometric spanner and utilize Extreme Value Theory to stochastically estimate its maximum empirical stretch factor. This allows us to mathematically bound the maximum distance of true nearest neighbors. Extensive evaluations on benchmark datasets demonstrate that our tiered framework delivers the average-case speed of HNSW while ensuring the worst-case correctness of exact search and outperforming other applicable approaches.

cs.DB↗

arXiv2026

Can we trust LLM Self-Explanations for Entity Resolution?

Large Language Models (LLMs) have recently shown strong performance on Entity Resolution (ER). Additionally, akin to their prowess in providing accurate predictions, these models often generate self-explanations alongside their predictions through prompting. While such self-explanations are appealing due to their negligible computational cost, their actual reliability remains largely unexplored. In this paper, we present the first large-scale systematic evaluation of LLM self-explanations for ER, focusing on feature attribution and counterfactual explanations at both the attribute and token levels. Across three LLMs, ten datasets, and multiple prompting strategies, we show that self-explanations are often unstable, weakly faithful, and poorly aligned with counterfactual evidence, revealing a substantial gap between plausibility and causal relevance. We further demonstrate that established post-hoc explanation methods provide significantly higher trustworthiness, but at a prohibitive computational cost when applied to LLMs. To bridge this gap, we introduce \uncerta{}, a hybrid explanation framework that leverages self-explanations as priors to guide post-hoc exploration. \uncerta{} achieves explanation quality comparable to post-hoc methods while reducing cost by up to an order of magnitude.

cs.DB↗

arXiv2026

Navigating the Shift: A Comparative Analysis of Web Search and Generative AI Response Generation

The rise of generative AI as a primary information source presents a paradigm shift from traditional web search. This paper presents a large-scale empirical study quantifying the fundamental differences between the results returned by Google Search and leading generative AI services. We analyze multiple dimensions, demonstrating that AI-generated answers and web search results diverge significantly in their consulted source domains, the typology of these domains (e.g., earned media vs. owned, social), query intent, and the freshness of the information provided. We then investigate the role of LLM pre-training as a key factor shaping these differences, analyzing how this intrinsic knowledge base interacts with and influences real-time web search when enabled. Our findings reveal the distinct mechanics of these two information ecosystems, leading to critical observations on the emergent field of Answer Engine Optimization (AEO) and its contrast with traditional Search Engine Optimization (SEO).

cs.IR↗

arXiv2025

Relational Deep Dive: Error-Aware Queries Over Unstructured Data

Unstructured data is pervasive, but analytical queries demand structured representations, creating a significant extraction challenge. Existing methods like RAG lack schema awareness and struggle with cross-document alignment, leading to high error rates. We propose ReDD (Relational Deep Dive), a framework that dynamically discovers query-specific schemas, populates relational tables, and ensures error-aware extraction with provable guarantees. ReDD features a two-stage pipeline: (1) Iterative Schema Discovery (ISD) identifies minimal, joinable schemas tailored to each query, and (2) Tabular Data Population (TDP) extracts and corrects data using lightweight classifiers trained on LLM hidden states. A main contribution of ReDD is SCAPE, a statistically calibrated method for error detection with coverage guarantees, and SCAPE-HYB, a hybrid approach that optimizes the trade-off between accuracy and human correction costs. Experiments across diverse datasets demonstrate ReDD's effectiveness, reducing data extraction errors from up to 30% to below 1% while maintaining high schema completeness (100% recall) and precision. ReDD's modular design enables fine-grained control over accuracy-cost trade-offs, making it a robust solution for high-stakes analytical queries over unstructured corpora.

cs.DB↗

arXiv2025

Generative Engine Optimization: How to Dominate AI Search

The rapid adoption of generative AI-powered search engines like ChatGPT, Perplexity, and Gemini is fundamentally reshaping information retrieval, moving from traditional ranked lists to synthesized, citation-backed answers. This shift challenges established Search Engine Optimization (SEO) practices and necessitates a new paradigm, which we term Generative Engine Optimization (GEO). This paper presents a comprehensive comparative analysis of AI Search and traditional web search (Google). Through a series of large-scale, controlled experiments across multiple verticals, languages, and query paraphrases, we quantify critical differences in how these systems source information. Our key findings reveal that AI Search exhibit a systematic and overwhelming bias towards Earned media (third-party, authoritative sources) over Brand-owned and Social content, a stark contrast to Google's more balanced mix. We further demonstrate that AI Search services differ significantly from each other in their domain diversity, freshness, cross-language stability, and sensitivity to phrasing. Based on these empirical results, we formulate a strategic GEO agenda. We provide actionable guidance for practitioners, emphasizing the critical need to: (1) engineer content for machine scannability and justification, (2) dominate earned media to build AI-perceived authority, (3) adopt engine-specific and language-aware strategies, and (4) overcome the inherent "big brand bias" for niche players. Our work provides the foundational empirical analysis and a strategic framework for achieving visibility in the new generative search landscape.

cs.IR↗

arXiv2025

Reliable Text-to-SQL with Adaptive Abstention

Large language models (LLMs) have revolutionized natural language interfaces for databases, particularly in text-to-SQL conversion. However, current approaches often generate unreliable outputs when faced with ambiguity or insufficient context. We present Reliable Text-to-SQL (RTS), a novel framework that enhances query generation reliability by incorporating abstention and human-in-the-loop mechanisms. RTS focuses on the critical schema linking phase, which aims to identify the key database elements needed for generating SQL queries. It autonomously detects potential errors during the answer generation process and responds by either abstaining or engaging in user interaction. A vital component of RTS is the Branching Point Prediction (BPP) which utilizes statistical conformal techniques on the hidden layers of the LLM model for schema linking, providing probabilistic guarantees on schema linking accuracy. We validate our approach through comprehensive experiments on the BIRD benchmark, demonstrating significant improvements in robustness and reliability. Our findings highlight the potential of combining transparent-box LLMs with human-in-the-loop processes to create more robust natural language interfaces for databases. For the BIRD benchmark, our approach achieves near-perfect schema linking accuracy, autonomously involving a human when needed. Combined with query generation, we demonstrate that near-perfect schema linking and a small query generation model can almost match SOTA accuracy achieved with a model orders of magnitude larger than the one we use.

cs.DB↗

arXiv2024

WeShap: Weak Supervision Source Evaluation with Shapley Values

Efficient data annotation stands as a significant bottleneck in training contemporary machine learning models. The Programmatic Weak Supervision (PWS) pipeline presents a solution by utilizing multiple weak supervision sources to automatically label data, thereby expediting the annotation process. Given the varied contributions of these weak supervision sources to the accuracy of PWS, it is imperative to employ a robust and efficient metric for their evaluation. This is crucial not only for understanding the behavior and performance of the PWS pipeline but also for facilitating corrective measures. In our study, we introduce WeShap values as an evaluation metric, which quantifies the average contribution of weak supervision sources within a proxy PWS pipeline, leveraging the theoretical underpinnings of Shapley values. We demonstrate efficient computation of WeShap values using dynamic programming, achieving quadratic computational complexity relative to the number of weak supervision sources. Our experiments demonstrate the versatility of WeShap values across various applications, including the identification of beneficial or detrimental labeling functions, refinement of the PWS pipeline, and rectification of mislabeled data. Furthermore, WeShap values aid in comprehending the behavior of the PWS pipeline and scrutinizing specific instances of mislabeled data. Although initially derived from a specific proxy PWS pipeline, we empirically demonstrate the generalizability of WeShap values to other PWS pipeline configurations. Our findings indicate a noteworthy average improvement of 5.0 points in downstream model accuracy through the revision of the PWS pipeline compared to previous state-of-the-art methods, underscoring the efficacy of WeShap values in enhancing data quality for training machine learning models.

cs.LG↗

arXiv2024

AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs

Pre-trained Large Language Models (LLMs) have significantly advanced natural language processing capabilities but are susceptible to biases present in their training data, leading to unfair outcomes in various applications. While numerous strategies have been proposed to mitigate bias, they often require extensive computational resources and may compromise model performance. In this work, we introduce AXOLOTL, a novel post-processing framework, which operates agnostically across tasks and models, leveraging public APIs to interact with LLMs without direct access to internal parameters. Through a three-step process resembling zero-shot learning, AXOLOTL identifies biases, proposes resolutions, and guides the model to self-debias its outputs. This approach minimizes computational costs and preserves model performance, making AXOLOTL a promising tool for debiasing LLM outputs with broad applicability and ease of use.

cs.CL↗

arXiv2024

ActiveDP: Bridging Active Learning and Data Programming

Modern machine learning models require large labelled datasets to achieve good performance, but manually labelling large datasets is expensive and time-consuming. The data programming paradigm enables users to label large datasets efficiently but produces noisy labels, which deteriorates the downstream model's performance. The active learning paradigm, on the other hand, can acquire accurate labels but only for a small fraction of instances. In this paper, we propose ActiveDP, an interactive framework bridging active learning and data programming together to generate labels with both high accuracy and coverage, combining the strengths of both paradigms. Experiments show that ActiveDP outperforms previous weak supervision and active learning approaches and consistently performs well under different labelling budgets.

cs.LG↗

arXiv2023

A Distributed Solution for Efficient K Shortest Paths Computation over Dynamic Road Networks

The problem of identifying the k-shortest paths KSPs for short in a dynamic road network is essential to many location-based services. Road networks are dynamic in the sense that the weights of the edges in the corresponding graph constantly change over time, representing evolving traffic conditions. Very often such services have to process numerous KSP queries over large road networks at the same time, thus there is a pressing need to identify distributed solutions for this problem. However, most existing approaches are designed to identify KSPs on a static graph in a sequential manner, restricting their scalability and applicability in a distributed setting. We therefore propose KSP-DG, a distributed algorithm for identifying k-shortest paths in a dynamic graph. It is based on partitioning the entire graph into smaller subgraphs, and reduces the problem of determining KSPs into the computation of partial KSPs in relevant subgraphs, which can execute in parallel on a cluster of servers. A distributed two-level index called DTLP is developed to facilitate the efficient identification of relevant subgraphs. A salient feature of DTLP is that it indexes a set of virtual paths that are insensitive to varying traffic conditions in an efficient and compact fashion, leading to very low maintenance cost in dynamic road networks. This is the first treatment of the problem of processing KSP queries over dynamic road networks. Extensive experiments conducted on real road networks confirm the superiority of our proposal over baseline methods.

cs.DB↗

arXiv2023

Can Large Language Models Design Accurate Label Functions?

Programmatic weak supervision methodologies facilitate the expedited labeling of extensive datasets through the use of label functions (LFs) that encapsulate heuristic data sources. Nonetheless, the creation of precise LFs necessitates domain expertise and substantial endeavors. Recent advances in pre-trained language models (PLMs) have exhibited substantial potential across diverse tasks. However, the capacity of PLMs to autonomously formulate accurate LFs remains an underexplored domain. In this research, we address this gap by introducing DataSculpt, an interactive framework that harnesses PLMs for the automated generation of LFs. Within DataSculpt, we incorporate an array of prompting techniques, instance selection strategies, and LF filtration methods to explore the expansive design landscape. Ultimately, we conduct a thorough assessment of DataSculpt's performance on 12 real-world datasets, encompassing a range of tasks. This evaluation unveils both the strengths and limitations of contemporary PLMs in LF design.

cs.CL↗

arXiv2022

Distributed Processing of k Shortest Path Queries over Dynamic Road Networks

The problem of identifying the k-shortest paths (KSPs for short) in a dynamic road network is essential to many location-based services. Road networks are dynamic in the sense that the weights of the edges in the corresponding graph constantly change over time, representing evolving traffic conditions. Very often such services have to process numerous KSP queries over large road networks at the same time, thus there is a pressing need to identify distributed solutions for this problem. However, most existing approaches are designed to identify KSPs on a static graph in a sequential manner (i.e., the (i+1)-th shortest path is generated based on the i-th shortest path), restricting their scalability and applicability in a distributed setting. We therefore propose KSP-DG, a distributed algorithm for identifying k-shortest paths in a dynamic graph. It is based on partitioning the entire graph into smaller subgraphs, and reduces the problem of determining KSPs into the computation of partial KSPs in relevant subgraphs, which can execute in parallel on a cluster of servers. A distributed two-level index called DTLP is developed to facilitate the efficient identification of relevant subgraphs. A salient feature of DTLP is that it indexes a set of virtual paths that are insensitive to varying traffic conditions, leading to very low maintenance cost in dynamic road networks. This is the first treatment of the problem of processing KSP queries over dynamic road networks. Extensive experiments conducted on real road networks confirm the superiority of our proposal over baseline methods.

cs.DB↗

arXiv2022

Effective Explanations for Entity Resolution Models

Entity resolution (ER) aims at matching records that refer to the same real-world entity. Although widely studied for the last 50 years, ER still represents a challenging data management problem, and several recent works have started to investigate the opportunity of applying deep learning (DL) techniques to solve this problem. In this paper, we study the fundamental problem of explainability of the DL solution for ER. Understanding the matching predictions of an ER solution is indeed crucial to assess the trustworthiness of the DL model and to discover its biases. We treat the DL model as a black box classifier and - while previous approaches to provide explanations for DL predictions are agnostic to the classification task. we propose the CERTA approach that is aware of the semantics of the ER problem. Our approach produces both saliency explanations, which associate each attribute with a saliency score, and counterfactual explanations, which provide examples of values that can flip the prediction. CERTA builds on a probabilistic framework that aims at computing the explanations evaluating the outcomes produced by using perturbed copies of the input records. We experimentally evaluate CERTA's explanations of state-of-the-art ER solutions based on DL models using publicly available datasets, and demonstrate the effectiveness of CERTA over recently proposed methods for this problem.

cs.DB↗

arXiv2021

LES3: Learning-based Exact Set Similarity Search

Set similarity search is a problem of central interest to a wide variety of applications such as data cleaning and web search. Past approaches on set similarity search utilize either heavy indexing structures, incurring large search costs or indexes that produce large candidate sets. In this paper, we design a learning-based exact set similarity search approach, LES3. Our approach first partitions sets into groups, and then utilizes a light-weight bitmap-like indexing structure, called token-group matrix (TGM), to organize groups and prune out candidates given a query set. In order to optimize pruning using the TGM, we analytically investigate the optimal partitioning strategy under certain distributional assumptions. Using these results, we then design a learning-based partitioning approach called L2P and an associated data representation encoding, PTR, to identify the partitions. We conduct extensive experiments on real and synthetic datasets to fully study LES3, establishing the effectiveness and superiority over other applicable approaches.

cs.DB↗

arXiv2021

Data Acquisition for Improving Machine Learning Models

The vast advances in Machine Learning over the last ten years have been powered by the availability of suitably prepared data for training purposes. The future of ML-enabled enterprise hinges on data. As such, there is already a vibrant market offering data annotation services to tailor sophisticated ML models. In this paper, we present research on the practical problem of obtaining data in order to improve the accuracy of ML models. We consider an environment in which consumers query for data to enhance the accuracy of their models and data providers who possess data make them available for training purposes. We first formalize this interaction process laying out the suitable framework and associated parameters for data exchange. We then propose two data acquisition strategies that consider a trade-off between exploration during which we obtain data to learn about the distribution of a provider's data and exploitation during which we optimize our data inquiries utilizing the gained knowledge. In the first strategy, Estimation and Allocation, we utilize queries to estimate the utilities of various predicates while learning about the distribution of the provider's data; then we proceed to the allocation stage in which we utilize those learned utility estimates to inform our data acquisition decisions. The second algorithmic proposal, named Sequential Predicate Selection, utilizes a sampling strategy to explore the distribution of the provider's data, adaptively investing more resources to parts of the data space that are statistically more promising to improve overall model accuracy. We present a detailed experimental evaluation of our proposals utilizing a variety of ML models and associated real data sets exploring all applicable parameters of interest. We identify trade-offs and highlight the relative benefits of each algorithm to further optimize model accuracy.

cs.DB↗

arXiv2021

Efficient Construction of Nonlinear Models over Normalized Data

Machine Learning (ML) applications are proliferating in the enterprise. Relational data which are prevalent in enterprise applications are typically normalized; as a result, data has to be denormalized via primary/foreign-key joins to be provided as input to ML algorithms. In this paper, we study the implementation of popular nonlinear ML models, Gaussian Mixture Models (GMM) and Neural Networks (NN), over normalized data addressing both cases of binary and multi-way joins over normalized relations. For the case of GMM, we show how it is possible to decompose computation in a systematic way both for binary joins and for multi-way joins to construct mixture models. We demonstrate that by factoring the computation, one can conduct the training of the models much faster compared to other applicable approaches, without any loss in accuracy. For the case of NN, we propose algorithms to train the network taking normalized data as the input. Similarly, we present algorithms that can conduct the training of the network in a factorized way and offer performance advantages. The redundancy introduced by denormalization can be exploited for certain types of activation functions. However, we demonstrate that attempting to explore this redundancy is helpful up to a certain point; exploring redundancy at higher layers of the network will always result in increased costs and is not recommended. We present the results of a thorough experimental evaluation, varying several parameters of the input relations involved and demonstrate that our proposals for the training of GMM and NN yield drastic performance improvements typically starting at 100%, which become increasingly higher as parameters of the underlying data vary, without any loss in accuracy.

cs.LG↗

arXiv2020

Top-k queries over digital traces

Recent advances in social and mobile technology have enabled an abundance of digital traces (in the form of mobile check-ins, association of mobile devices to specific WiFi hotspots, etc.) revealing the physical presence history of diverse sets of entities (e.g., humans, devices, and vehicles). One challenging yet important task is to identify k entities that are most closely associated with a given query entity based on their digital traces. We propose a suite of indexing techniques and algorithms to enable fast query processing for this problem at scale. We first define a generic family of functions measuring the association between entities, and then propose algorithms to transform digital traces into a lower-dimensional space for more efficient computation. We subsequently design a hierarchical indexing structure to organize entities in a way that closely associated entities tend to appear together. We then develop algorithms to process top-k queries utilizing the index. We theoretically analyze the pruning effectiveness of the proposed methods based on a mobility model which we propose and validate in real life situations. Finally, we conduct extensive experiments on both synthetic and real datasets at scale, evaluating the performance of our techniques both analytically and experimentally, confirming the effectiveness and superiority of our approach over other applicable approaches across a variety of parameter settings and datasets.

cs.DB↗

arXiv2020

Evaluating Temporal Queries Over Video Feeds

Recent advances in Computer Vision and Deep Learning made possible the efficient extraction of a schema from frames of streaming video. As such, a stream of objects and their associated classes along with unique object identifiers derived via object tracking can be generated, providing unique objects as they are captured across frames. In this paper we initiate a study of temporal queries involving objects and their co-occurrences in video feeds. For example, queries that identify video segments during which the same two red cars and the same two humans appear jointly for five minutes are of interest to many applications ranging from law enforcement to security and safety. We take the first step and define such queries in a way that they incorporate certain physical aspects of video capture such as object occlusion. We present an architecture consisting of three layers, namely object detection/tracking, intermediate data generation and query evaluation. We propose two techniques,MFS and SSG, to organize all detected objects in the intermediate data generation layer, which effectively, given the queries, minimizes the number of objects and frames that have to be considered during query evaluation. We also introduce an algorithm called State Traversal (ST) that processes incoming frames against the SSG and efficiently prunes objects and frames unrelated to query evaluation, while maintaining all states required for succinct query evaluation. We present the results of a thorough experimental evaluation utilizing both real and synthetic data establishing the trade-offs between MFS and SSG. We stress various parameters of interest in our evaluation and demonstrate that the proposed query evaluation methodology coupled with the proposed algorithms is capable to evaluate temporal queries over video feeds efficiently, achieving orders of magnitude performance benefits.

cs.DB↗