REVIEW 15 cited by
ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
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.
Forward citations
Cited by 15 Pith papers
-
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
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.
-
LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction
Label-aware diagnostic reflection plus two-stage outcome GRPO improves same-backbone IE F1 over SFT, with larger gains under relation-extraction domain shift.
-
An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous Documents
An ontology-guided, deduplication-aware extraction pipeline for heterogeneous documents reports 70–95% search recall and zero false merges on synthetic intelligence corpora.
-
Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction
KRPO iteratively optimizes LLM prompts via NLI feedback on triplet-restored sentences and canonicalizes relations with a dynamic memory, reporting higher F1 than EDC on WebNLG, REBEL, and Wiki-NRE.
-
BioPIE: A Biomedical Protocol Information Extraction Dataset for Experiment Understanding
A new protocol-centric knowledge-graph dataset (34 entity types, 21 relations, 509 protocols) improves biomedical experiment QA over text-only retrieval.
-
Keyword-Centric Prompting for One-Shot Event Detection with Self-Generated Rationale Enhancements
A keyword-centric prompting method with self-generated propose-and-judge rationales improves one-shot event detection F1 by up to 12.8 points over prior in-context learning baselines.
-
Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
Syntactic similarity retrieval of demonstrations improves LLM-based automatic term extraction in cross-domain settings, but gains are modest and in-domain lexical retrieval is often competitive or better.
-
Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering
FOCUS improves VQA accuracy by routing easy questions through fast zero-shot answering and hard questions through question-conditioned image segmentation before the final answer.
-
GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction
A fully automated pipeline for generating annotation schemas, guidelines, and synthetic labeled examples from documents improves zero-shot NER after fine-tuning.
-
DE-NER : Zero-shot Named Entity Recognition via Dialogue Elicitation of Large Language Models
A self-play dialogue framework with a self-trained questioner improves zero-shot named entity recognition over basic prompting, but not consistently over the strongest existing methods.
-
Assessment of Generative Named Entity Recognition in the Era of Large Language Models
Fine-tuned open-source LLMs using inline bracketed or XML formats match traditional NER models on flat and nested named-entity recognition, with only small drops when labels are replaced by symbols.
-
Joint Information Extraction Across Classical and Modern Chinese with Tea-MOELoRA
Tea-MOELORA uses separate task and era gates over LoRA experts to jointly train relation and event extraction across classical and modern Chinese, improving F1 over joint LoRA and existing LoRA-MoE baselines on most datasets.
-
A Variational Approach for Mitigating Entity Bias in Relation Extraction
A variational information bottleneck that maps entity tokens to stochastic Gaussian embeddings with a blending factor improves relation extraction F1 on general, financial, and biomedical datasets, especially under en...
-
Enhancing Generative Information Extraction with Two-step Validation: A Product Attribute Use Case
Reformulating generative product IE as LLM correction of PLM drafts improves F1 on weakly expressed attributes and lets mid-size local models approach larger ones.
-
The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs
A structured survey of LLM safety evaluation that proposes a why/what/where/how taxonomy and catalogs metrics, datasets, benchmarks, evaluators, and frameworks.
Discussion (0). Continue with ORCID to comment.