Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction

2024-02-21 · Guozheng Li, Wenjun Ke, Peng Wang, Zijie Xu, Ke Ji, Jiajun Liu, Ziyu Shang, Qiqing Luo

The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples.

📄 PDF Abstract BibTeX arXiv:2402.13741

Code (0)

등록된 구현이 없습니다.

Tasks

BlockingIn-Context LearningRTE

RDBLearn: Simple In-Context Prediction Over Relational Databases

2026-02-14 · Yanlin Zhang, Linjie Xu, Quan Gan, David Wipf 외 arxiv

Recent advances in tabular in-context learning (ICL) show that a single pretrained model can adapt to new prediction tasks from a small set of labeled examples, avoiding per-task training and heavy tuning. However, many …

TabPFGen -- Tabular Data Generation with TabPFN

2024-06-07 · Junwei Ma, Apoorv Dankar, George Stein, Guangwei Yu 외

Advances in deep generative modelling have not translated well to tabular data. We argue that this is caused by a mismatch in structure between popular generative models and discriminative models of tabular data. We thus…

Data Augmentation Imputation In-Context Learning Tabular Data Generation

SALT-KG: A Benchmark for Semantics-Aware Learning on Enterprise Tables

2026-01-12 · Isaiah Onando Mulang, Felix Sasaki, Tassilo Klein, Jonas Kolk 외 arxiv

Building upon the SALT benchmark for relational prediction (Klein et al., 2024), we introduce SALT-KG, a benchmark for semantics-aware learning on enterprise tables. SALT-KG extends SALT by linking its multi-table transa…

REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformers

2023-02-04 · Aivin V. Solatorio, Olivier Dupriez

Tabular data is a common form of organizing data. Multiple models are available to generate synthetic tabular datasets where observations are independent, but few have the ability to produce relational datasets. Modeling…

Synthetic Data Generation

FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks

2026-06-29 · Marek Polewczyk, Maximilian Schambach, Marco Spinaci, Sam Thelin 외 arxiv

We introduce FlexTab, a flexible encoder-decoder architecture for in-context learning on tabular data that pairs a single, task-agnostic encoder with a suite of task-specific decoders. Unlike existing tabular in-context …

Anomaly Detection