An adaptive two-phase semantic filter using clustering then a hybrid proxy trained on LLM confidence achieves 1.6-2.0x speedup over prior methods at 90% accuracy on 10K document corpora.
Chatie: Zero-shot information extraction via chatting with chatgpt
13 Pith papers cite this work, alongside 145 external citations. Polarity classification is still indexing.
13
Pith papers citing it
145
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A curriculum knowledge graph extracted from official Chinese K-12 textbooks yields a 23,640-question benchmark on which top LLMs score at most 57% exact match, and a 2,300-sample training set that outperforms eight general instruction corpora on educational benchmarks.
LC-ICL improves few-shot NER and RE by using label-guided contrastive demonstrations that pair positive samples with error-annotated negative samples.
BCL introduces a particle-filtering Bayesian update framework to systematically refine label representations in in-context learning for information extraction, claiming consistent gains over prior methods.
Relational Probing replaces the LM output head with a trainable relation head that induces graphs from hidden states and optimizes them end-to-end for stock trend prediction, showing gains over co-occurrence baselines.
Translates SemEval-2010 Task 8 to Romanian and evaluates Gemma 31B prompting and QLoRA fine-tuning against encoder baselines, finding fine-tuning reduces the cross-lingual gap to 1.4pp while smaller models perform within 1-4pp.
SSDAU is a new data augmentation method for JERE that uses entity-based segmentation, context-aware semantic encoding, entity restructuring, and BERTTopic filtering to produce more robust augmented data than prior baselines.
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.
SchemaRAG dynamically reduces large schemas via RAG for LLM information extraction, reporting up to 8.8% micro-F1 gain, 47% latency cut, and 48% token cost reduction on healthcare and e-commerce data.
Graph-based parsers outperform LLMs on supervised relation extraction as linguistic graph complexity grows with more relations per document.
A multi-step LLM-based pipeline constructs the first knowledge graph for nuclear fusion energy and enables RAG for multi-hop queries.
citing papers explorer
-
Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method
An adaptive two-phase semantic filter using clustering then a hybrid proxy trained on LLM confidence achieves 1.6-2.0x speedup over prior methods at 90% accuracy on 10K document corpora.
-
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
A curriculum knowledge graph extracted from official Chinese K-12 textbooks yields a 23,640-question benchmark on which top LLMs score at most 57% exact match, and a 2,300-sample training set that outperforms eight general instruction corpora on educational benchmarks.
-
LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction
LC-ICL improves few-shot NER and RE by using label-guided contrastive demonstrations that pair positive samples with error-annotated negative samples.
-
BCL: Bayesian In-Context Learning Framework for Information Extraction
BCL introduces a particle-filtering Bayesian update framework to systematically refine label representations in in-context learning for information extraction, claiming consistent gains over prior methods.
-
Relational Probing: LM-to-Graph Adaptation for Financial Prediction
Relational Probing replaces the LM output head with a trainable relation head that induces graphs from hidden states and optimizes them end-to-end for stock trend prediction, showing gains over co-occurrence baselines.
-
Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian
Translates SemEval-2010 Task 8 to Romanian and evaluates Gemma 31B prompting and QLoRA fine-tuning against encoder baselines, finding fine-tuning reduces the cross-lingual gap to 1.4pp while smaller models perform within 1-4pp.
-
SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
SSDAU is a new data augmentation method for JERE that uses entity-based segmentation, context-aware semantic encoding, entity restructuring, and BERTTopic filtering to produce more robust augmented data than prior baselines.
-
Task Decomposition for Efficient Annotation
Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.
-
SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction
SchemaRAG dynamically reduces large schemas via RAG for LLM information extraction, reporting up to 8.8% micro-F1 gain, 47% latency cut, and 48% token cost reduction on healthcare and e-commerce data.
-
LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs
Graph-based parsers outperform LLMs on supervised relation extraction as linguistic graph complexity grows with more relations per document.
-
Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information
A multi-step LLM-based pipeline constructs the first knowledge graph for nuclear fusion energy and enables RAG for multi-hop queries.
- TCMIIES: A Browser-Based LLM-Powered Intelligent Information Extraction System for Academic Literature
- EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain