GPT-NER: Named Entity Recognition via Large Language Models
Reviewed by Pithpith:S5TM65EKopen to challenge →
read the original abstract
Despite the fact that large-scale Language Models (LLM) have achieved SOTA performances on a variety of NLP tasks, its performance on NER is still significantly below supervised baselines. This is due to the gap between the two tasks the NER and LLMs: the former is a sequence labeling task in nature while the latter is a text-generation model. In this paper, we propose GPT-NER to resolve this issue. GPT-NER bridges the gap by transforming the sequence labeling task to a generation task that can be easily adapted by LLMs e.g., the task of finding location entities in the input text "Columbus is a city" is transformed to generate the text sequence "@@Columbus## is a city", where special tokens @@## marks the entity to extract. To efficiently address the "hallucination" issue of LLMs, where LLMs have a strong inclination to over-confidently label NULL inputs as entities, we propose a self-verification strategy by prompting LLMs to ask itself whether the extracted entities belong to a labeled entity tag. We conduct experiments on five widely adopted NER datasets, and GPT-NER achieves comparable performances to fully supervised baselines, which is the first time as far as we are concerned. More importantly, we find that GPT-NER exhibits a greater ability in the low-resource and few-shot setups, when the amount of training data is extremely scarce, GPT-NER performs significantly better than supervised models. This demonstrates the capabilities of GPT-NER in real-world NER applications where the number of labeled examples is limited.
This paper has not been read by Pith yet.
Forward citations
Cited by 12 Pith papers
-
AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models
AutoVerifier decomposes technical claims into triples and uses layered LLM verification to assess validity, demonstrated on a quantum computing paper by finding overclaims and conflicts.
-
KRONE: Scalable LLM-Augmented Log Anomaly Detection via Hierarchical Abstraction
KRONE derives semantic execution hierarchies from flat logs to enable modular multi-level anomaly detection with hybrid local and nested-aware detectors plus limited LLM use, delivering 10% F1 gains and over 100x data...
-
AutoSpecNER: A Fine-Grained Named Entity Recognition Dataset for Vehicle Specification Extraction
AutoSpecNER is a new fine-grained NER dataset for vehicle advertisements with 659 examples and 15 categories, where DeBERTa reaches 90% micro-F1 versus 43% for rules and 77.8% for the best LLM.
-
Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
Faithfulness-QA is a 99k-sample dataset created via counterfactual entity substitution on existing QA benchmarks to train and evaluate context-faithful RAG models.
-
An Agentic Workflow for Detecting Personally Identifiable Information in Crash Narratives
A hybrid agentic workflow using Presidio for structured PII and fine-tuned LLMs plus verification for names, addresses, and identifiers detects PII in crash narratives at 0.82 precision and 0.94 recall.
-
DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition
DynamicNER is a dynamic-categorization multilingual NER dataset with 155 entity types paired with CascadeNER, a two-stage lightweight LLM method claiming higher fine-grained accuracy.
-
MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis
MSMO framework achieves claimed SOTA cross-lingual ABSA via sentence- and aspect-level alignment, code-switching, consistency training, and knowledge distillation.
-
How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions
Qwen 3.5 4B reaches 96.60% F1 on merchant information extraction after LoRA fine-tuning, within 0.35 points of the LLaMA 3.1-8B baseline at 96.95%, with smaller models showing usable accuracy-latency trade-offs.
-
Naamah: A Large Scale Synthetic Sanskrit NER Corpus via DBpedia Seeding and LLM Generation
Naamah is a silver-standard Sanskrit NER dataset of 102,942 sentences generated by seeding DBpedia entities into a 24B-parameter LLM to produce grammatically natural training data, then used to benchmark XLM-RoBERTa a...
-
Beyond the Basics: Leveraging Large Language Model for Fine-Grained Medical Entity Recognition
Fine-tuned LLaMA3 with LoRA reaches 81.24% F1 on 18-category fine-grained medical entity recognition, beating zero-shot by 63.11% and few-shot by 35.63%.
-
Universal NER v2: Towards a Massively Multilingual Named Entity Recognition Benchmark
Universal NER v2 expands a multilingual NER benchmark with consistent cross-lingual annotations collected through an active community of organizers and annotators.
-
Benchmark Data Contamination of Large Language Models: A Survey
A survey reviewing benchmark data contamination in LLMs, its impact on evaluation, and alternative assessment approaches.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.