Downstream tasks with LLM

Dataset

1. Is GPT-3 a Good Data Annotator? [paper]
2. ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks [paper]
3. Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction [paper]

IE

1. ZCODE4STRUCT: Code Generation for Few-Shot Structured Prediction from Natural Language [paper]
2. Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction [paper]
3. Zero-Shot Information Extraction via Chatting with ChatGPT [paper][code]
4. Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples! [paper]
5. Thinking about GPT-3 in-context learning for biomedical IE? [paper[ code
6. Lauge language models are fewshot clinical Information Extractors [paper]
7. Zero-shot Clinical Entity Recognition using ChatGPT [paper]
8. Yes but.. Can ChatGPT Identify Entities in Historical Documents? [paper]
9. Evaluation-of-ChatGPT-on-Information-Extraction [paper]
10. Improving Chatbot Responses with Information Extraction [paper]
11. https://huggingface.co/spaces/Shad0ws/Information_Extraction_with_ChatGPT
12. GPT4IE [code]

Summarization

1. ChatGPT as a Factual Inconsistency Evaluator for Abstractive Text Summarization [paper]
2. Large Language Models are Diverse Role-Players for Summarization Evaluation [paper]

Machine Translation

1. Towards Making the Most of ChatGPT for Machine Translation [paper]
2. Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models: A Case Study on ChatGPT [paper]

Error Correction

1. ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark [paper]
2. An Analysis of GPT-3's Performance in Grammatical Error Correction [paper]

Others

1. Is chatgpt a general-purpose natural language processing task solver?
2. Comprehensive Capability Analysis of GPT-3 and GPT-3.5 SeriesModels [paper]
3. ChatDoctor: A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain [paper]