Relational Task Generation Language: A Declarative Specification Framework for Relational Deep Learning

• URL: http://arxiv.org/abs/2609.01292v1
• Date: Tue, 01 Sep 2026 14:27:06 GMT
• Title: Relational Task Generation Language: A Declarative Specification Framework for Relational Deep Learning
• Abstract summary: Deep Learning (DL) has become a powerful paradigm for learning from multitabular data.<n>RTGL is an open-source declarative language for RDL task formulation.<n>We demonstrate the practical utility of RTGL by designing various new tasks with diverse forms and target types.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Relational Deep Learning (RDL) has become a powerful paradigm for learning from multi-tabular data. However, manually defining RDL prediction tasks is a laborious process that frequently results in data leakage. To address this issue, we introduce Relational Task Generation Language (RTGL) - an open-source declarative language that streamlines RDL task formulation by abstracting away low-level SQL details. We showcase RTGL by reconstructing existing RDL benchmark tasks and uncovering their inconsistencies stemming from manually crafted SQL definitions of RDL prediction targets, thereby underscoring the value of a dedicated declarative language. In addition, we demonstrate the practical utility of RTGL by designing various new tasks with diverse forms and target types. Our experiments confirm the robustness and usability of RTGL, as well as its seamless integration with the existing RDL frameworks, making it widely accessible to the community.

Related papers

• Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation [19.750295463954853]
  Source-Grounded Semantic Reinforcement Learning (SG-SRL) is a resource-utilization framework that converts source-language monolingual data into cross-lingual semantic supervision for target-language generation.<n>SG-SRL performs reference-free reinforcement learning (RL) on source-language data using a cross-lingual semantic reward model.<n>Experiments on Chinese-to-Thai generation show that SG-SRL improves semantic grounding and factual coverage over cold-start SFT.
  arXiv  Detail & Related papers  (2026-05-28T07:27:16Z)
• RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases [49.47033473074821]
  We propose RelPrism, a multi-faceted self-supervised learning framework for RDBs.<n>RDB tasks often require multi-faceted information across different perspectives and granularities.<n>Our experiments show that RelPrism improves ROC-AUC by 4.15% for classification and reduces MAE by 10.75% for regression over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-22T05:19:58Z)
• BETA-Labeling for Multilingual Dataset Construction in Low-Resource IR [0.06363400715351396]
  This work presents a Bangla IR dataset constructed using a BETA-labeling framework.<n>We examine whether IR datasets from other low-resource languages can be effectively reused through one-hop machine translation.
  arXiv  Detail & Related papers  (2026-02-16T06:04:04Z)
• Task Arithmetic with Support Languages for Low-Resource ASR [2.0368746869445236]
  Existing approaches to many low-resource natural language processing tasks leverage additional data from higher-resource languages.<n>One increasingly popular approach uses task arithmetic to combine models trained on different tasks to create a model for a task where there is little to no training data.<n>In this paper, we consider training on a particular language to be a task, and we generate task vectors by fine-tuning variants of the Whisper ASR system.
  arXiv  Detail & Related papers  (2026-01-11T19:24:05Z)
• ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval [125.19156877994612]
  Generative retrieval (GR) reformulates information retrieval (IR) by framing it as the generation of document identifiers (docids)<n>We propose textscZeroGR, a zero-shot generative retrieval framework that leverages natural language instructions to extend GR across a wide range of IR tasks.<n>Specifically, textscZeroGR is composed of three key components: (i) an LM-based docid generator that unifies heterogeneous documents into semantically meaningful docids; (ii) an instruction-tuned query generator that generates diverse types of queries from natural language task descriptions to enhance
  arXiv  Detail & Related papers  (2025-10-12T03:04:24Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models [89.13128402847943]
  We present LUSIFER, a novel zero-shot approach that adapts LLM-based embedding models for multilingual tasks without requiring multilingual supervision.<n>LUSIFER's architecture combines a multilingual encoder, serving as a language-universal learner, with an LLM-based embedding model optimized for embedding-specific tasks.<n>We introduce a new benchmark encompassing 5 primary embedding tasks, 123 diverse datasets, and coverage across 14 languages.
  arXiv  Detail & Related papers  (2025-01-01T15:43:07Z)
• Interactive and Expressive Code-Augmented Planning with Large Language Models [62.799579304821826]
  Large Language Models (LLMs) demonstrate strong abilities in common-sense reasoning and interactive decision-making. Recent techniques have sought to structure LLM outputs using control flow and other code-adjacent techniques to improve planning performance. We propose REPL-Plan, an LLM planning approach that is fully code-expressive and dynamic.
  arXiv  Detail & Related papers  (2024-11-21T04:23:17Z)
• Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization [108.6908427615402]
  Cross-lingual summarization ( CLS) aims to generate a summary for the source text in a different target language.<n>Currently, instruction-tuned large language models (LLMs) excel at various English tasks.<n>Recent studies have shown that LLMs' performance on CLS tasks remains unsatisfactory even with few-shot settings.
  arXiv  Detail & Related papers  (2024-10-26T00:39:44Z)
• How Good are LLMs at Relation Extraction under Low-Resource Scenario? Comprehensive Evaluation [7.151108031568037]
  This paper constructs low-resource relation extraction datasets in 10 low-resource languages (LRLs) in three regions (Central Asia, Southeast Asia and Middle East) The corpora are constructed by translating the original publicly available English RE datasets (NYT10, FewRel and CrossRE) using an effective multilingual machine translation. Then, we use the language perplexity (PPL) to filter out the low-quality data from the translated datasets.
  arXiv  Detail & Related papers  (2024-06-17T03:02:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.