Tootfinder

NLGCL: Naturally Existing Neighbor Layers Graph Contrastive Learning for Recommendation
Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li, Hewei Wang, Wei Wang, Xiping Hu, Edith Ngai
https://arxiv.org/abs/2507.07522

NLGCL: Naturally Existing Neighbor Layers Graph Contrastive Learning for Recommendation
Graph Neural Networks (GNNs) are widely used in collaborative filtering to capture high-order user-item relationships. To address the data sparsity problem in recommendation systems, Graph Contrastive Learning (GCL) has emerged as a promising paradigm that maximizes mutual information between contrastive views. However, existing GCL methods rely on augmentation techniques that introduce semantically irrelevant noise and incur significant computational and storage costs, limiting effectiveness a…

Evaluating NL2SQL via SQL2NL
Mohammadtaher Safarzadeh, Afshin Oroojlooyjadid, Dan Roth
https://arxiv.org/abs/2509.04657 https://arxiv.org/pdf/2509.04657

Evaluating NL2SQL via SQL2NL
Robust evaluation in the presence of linguistic variation is key to understanding the generalization capabilities of Natural Language to SQL (NL2SQL) models, yet existing benchmarks rarely address this factor in a systematic or controlled manner. We propose a novel schema-aligned paraphrasing framework that leverages SQL-to-NL (SQL2NL) to automatically generate semantically equivalent, lexically diverse queries while maintaining alignment with the original schema and intent. This enables the fi…

Nonlocal Harnack inequalities for nonlocal double phase equations I ; with positive bounded modulating coefficient with no H\"older condition
Yong-Cheol Kim
https://arxiv.org/abs/2509.07433

Nonlocal Harnack inequalities for nonlocal double phase equations I ; with positive bounded modulating coefficient with no Hölder condition
In this paper, by applying the De Giorgi-Nash-Moser theory we prove nonlocal Harnack inequalities for (locally nonnegative in $Ω$) weak solutions to nolocal double phase equations \begin{equation*}\begin{cases}\cL u =0 & \text{ in $Ω$,} \\ u=g & \text{ in $\BR^n\sΩ$ } \end{cases}\end{equation*} where $Ω\subset\BR^n$ ($n\ge 2$) is a bounded domain with Lipschitz boundary, $\cL$ is the nonlocal double phase operator $\cL$ given by \begin{equation*}\begin{split}\cL u(x)=&\pv\int_{\BR^n}|u…

🇺🇦 Auf radioeins läuft...
Noel Gallagher's High Flying Birds:
🎵 Flying On The Ground
#NowPlaying #NoelGallaghersHighFlyingBirds
https://open.spotify.com/track/7uWfSTCp4jJzayH1Pd0RcW

Crosslisted article(s) found for cs.DB. https://arxiv.org/list/cs.DB/new
[1/1]:
- Evaluating NL2SQL via SQL2NL
Mohammadtaher Safarzadeh, Afshin Oroojlooyjadid, Dan Roth

🇺🇦 Auf radioeins läuft...
Noel Gallagher's High Flying Birds:
🎵 Council Skies (Radio Edit)
#NowPlaying #NoelGallaghersHighFlyingBirds
https://noelgallagher.bandcamp.com/album/council-skies
https://open.spotify.com/track/5fySmz9Qx8cpKaacHxEYN9

On indefinite Einstein solvmanifolds admitting a Killing spinor
Diego Conti, Federico A. Rossi, Romeo Segnan Dalmasso
https://arxiv.org/abs/2507.23714 https://

On indefinite Einstein solvmanifolds admitting a Killing spinor
Riemannian Einstein solvmanifolds can be described in terms of nilsolitons, namely nilpotent Lie groups endowed with a left-invariant Ricci soliton metric. This characterization does not extend to indefinite metrics; nonetheless, nilsolitons can be defined and used to construct Einstein solvmanifolds of a higher dimension in any signature. An Einstein solvmanifold obtained by this construction turns out to satisfy the pseudo-Iwasawa condition, meaning that its Lie algebra splits as the orthog…

Do LLMs Align with My Task? Evaluating Text-to-SQL via Dataset Alignment
Davood Rafiei, Morgan Lindsay Heisler, Weiwei Zhang, Mohammadreza Pourreza, Yong Zhang
https://arxiv.org/abs/2510.04919

Do LLMs Align with My Task? Evaluating Text-to-SQL via Dataset Alignment
Supervised Fine-Tuning (SFT) is an effective method for adapting Large Language Models (LLMs) on downstream tasks. However, variability in training data can hinder a model's ability to generalize across domains. This paper studies the problem of dataset alignment for Natural Language to SQL (NL2SQL or text to SQL), examining how well SFT training data matches the structural characteristics of target queries and how this alignment impacts model performance. We hypothesize that alignment can be a…

From NL2SQL to NL2GeoSQL: GeoSQL-Eval for automated evaluation of LLMs on PostGIS queries
Shuyang Hou, Haoyue Jiao, Ziqi Liu, Lutong Xie, Guanyu Chen, Shaowen Wu, Xuefeng Guan, Huayi Wu
https://arxiv.org/abs/2509.25264

From NL2SQL to NL2GeoSQL: GeoSQL-Eval for automated evaluation of LLMs on PostGIS queries
In recent years, large language models (LLMs) have achieved remarkable progress in natural language understanding and structured query generation (NL2SQL). However, extending these advances to GeoSQL tasks in the PostGIS environment remains challenging due to the complexity of spatial functions, geometric data types, and execution semantics. Existing evaluations primarily focus on general relational databases or Google Earth Engine code generation, leaving a lack of systematic benchmarks tailor…

RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
Zui Chen, Han Li, Xinhao Zhang, Xiaoyu Chen, Chunyin Dong, Yifeng Wang, Xin Cai, Su Zhang, Ziqi Li, Chi Ding, Jinxu Li, Shuai Wang, Dousheng Zhao, Sanhai Gao, Guangyi Liu
https://arxiv.org/abs/2508.17590

RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System
We present RubikSQL, a novel NL2SQL system designed to address key challenges in real-world enterprise-level NL2SQL, such as implicit intents and domain-specific terminology. RubikSQL frames NL2SQL as a lifelong learning task, demanding both Knowledge Base (KB) maintenance and SQL generation. RubikSQL systematically builds and refines its KB through techniques including database profiling, structured information extraction, agentic rule mining, and Chain-of-Thought (CoT)-enhanced SQL profiling.…