How much reliable is ChatGPT's prediction on Information Extraction under Input Perturbations?
Preprint
Abstract
In this paper, we assess the robustness (reliability) of ChatGPT under input perturbations for one of the most fundamental tasks of Information Extraction (IE) i.e. Named Entity Recognition (NER). Despite the hype, the majority of the researchers have vouched for its language understanding and generation capabilities; a little attention has been paid to understand its robustness: How the input-perturbations affect 1) the predictions, 2) the confidence of predictions and 3) the quality of rationale behind its prediction. We perform a systematic analysis of ChatGPT's robustness (under both zero-shot and few-shot setup) on two NER datasets using both automatic and human evaluation. Based on automatic evaluation metrics, we find that 1) ChatGPT is more brittle on Drug or Disease replacements (rare entities) compared to the perturbations on widely known Person or Location entities, 2) the quality of explanations for the same entity considerably differ under different types of "Entity-Specific" and "Context-Specific" perturbations and the quality can be significantly improved using in-context learning, and 3) it is overconfident for majority of the incorrect predictions, and hence it could lead to misguidance of the end-users.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reportsEuropean Radiology, 2023
- Will ChatGPT Get You Caught? Rethinking of Plagiarism Detection2023
- Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech2023
- A Novel Tensor Learning Model for Joint Relational Triplet ExtractionIEEE Transactions on Cybernetics, 2023
- RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models2021
- Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning2021
- Robust Named Entity Recognition with Truecasing PretrainingProceedings of the AAAI Conference on Artificial Intelligence, 2020
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension2020
- Relation-Aware Collaborative Learning for Unified Aspect-Based Sentiment Analysis2020
- BioCreative V CDR task corpus: a resource for chemical disease relation extractionDatabase: The Journal of Biological Databases and Curation, 2016