The reviewed record of science sign in
Pith

arxiv: 2302.10205 · v2 · pith:EQCZ6K6B · submitted 2023-02-20 · cs.CL

ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:EQCZ6K6Brecord.jsonopen to challenge →

classification cs.CL
keywords zero-shotmodelschatgptchatieextractionchallengingdatasetsframework
0
0 comments X
read the original abstract

Zero-shot information extraction (IE) aims to build IE systems from the unannotated text. It is challenging due to involving little human intervention. Challenging but worthwhile, zero-shot IE reduces the time and effort that data labeling takes. Recent efforts on large language models (LLMs, e.g., GPT-3, ChatGPT) show promising performance on zero-shot settings, thus inspiring us to explore prompt-based methods. In this work, we ask whether strong IE models can be constructed by directly prompting LLMs. Specifically, we transform the zero-shot IE task into a multi-turn question-answering problem with a two-stage framework (ChatIE). With the power of ChatGPT, we extensively evaluate our framework on three IE tasks: entity-relation triple extract, named entity recognition, and event extraction. Empirical results on six datasets across two languages show that ChatIE achieves impressive performance and even surpasses some full-shot models on several datasets (e.g., NYT11-HRL). We believe that our work could shed light on building IE models with limited resources.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Fast LLM-Based Semantic Filtering: From a Unified Framework to an Adaptive Two-Phase Method

    cs.DB 2026-06 unverdicted novelty 7.0

    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.

  2. K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs

    cs.CL 2026-05 conditional novelty 7.0

    K12-KGraph is a textbook-derived knowledge graph that powers a new benchmark revealing LLMs' poor curriculum cognition and a small training corpus that outperforms general instruction data on educational tasks.

  3. LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction

    cs.CL 2026-06 unverdicted novelty 6.0

    LC-ICL improves few-shot NER and RE by using label-guided contrastive demonstrations that pair positive samples with error-annotated negative samples.

  4. BCL: Bayesian In-Context Learning Framework for Information Extraction

    cs.CL 2026-06 unverdicted novelty 6.0

    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.

  5. Relational Probing: LM-to-Graph Adaptation for Financial Prediction

    cs.CL 2026-04 unverdicted novelty 6.0

    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.

  6. EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain

    cs.CL 2024-06 unverdicted novelty 6.0

    Introduces the SciEvents dataset for scientific event extraction and the EXCEEDS nugget-grid modeling framework that reports state-of-the-art results on the new data.

  7. Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian

    cs.CL 2026-06 unverdicted novelty 5.0

    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 wit...

  8. SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction

    cs.CL 2026-05 unverdicted novelty 5.0

    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.

  9. SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction

    cs.CL 2026-05 unverdicted novelty 5.0

    SSDAU is a new structured semantic data augmentation method that produces more robust training data for JERE models, showing smaller performance drops under ambiguity than seven baselines.

  10. Task Decomposition for Efficient Annotation

    cs.CL 2026-06 unverdicted novelty 4.0

    Decomposing annotation tasks using centers from centering theory reduces aggregate inferential load via a degrees-of-freedom model and enables better sub-task allocation.

  11. TCMIIES: A Browser-Based LLM-Powered Intelligent Information Extraction System for Academic Literature

    cs.CL 2026-05 unverdicted novelty 4.0

    TCMIIES is a zero-install browser platform with schema-guided LLM prompting that achieves over 94% structured output compliance for academic information extraction, including support for Chinese databases.

  12. SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction

    cs.IR 2026-05 unverdicted novelty 4.0

    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.

  13. LLMs Underperform Graph-Based Parsers on Supervised Relation Extraction for Complex Graphs

    cs.CL 2026-04 unverdicted novelty 4.0

    Graph-based parsers outperform LLMs on supervised relation extraction as linguistic graph complexity grows with more relations per document.

  14. Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information

    cs.CL 2025-04 unverdicted novelty 4.0

    A multi-step LLM-based pipeline constructs the first knowledge graph for nuclear fusion energy and enables RAG for multi-hop queries.