mlsanityData to 14 Oct 2026

The Limits of ChatGPT in Extracting Aspect-Category-Opinion-Sentiment Quadruples: A Comparative Analysis

arXiv 2310.06502 ↗First posted 10 Oct 2023cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Recently, ChatGPT has attracted great attention from both industry and academia due to its surprising abilities in natural language understanding and generation. We are particularly curious about whether it can achieve promising performance on one of the most complex tasks in aspect-based sentiment analysis, i.e., extracting aspect-category-opinion-sentiment quadruples from texts. To this end, in this paper we develop a specialized prompt template that enables ChatGPT to effectively tackle this complex quadruple extraction task. Further, we propose a selection method on few-shot examples to fully exploit the in-context learning ability of ChatGPT and uplift its effectiveness on this complex task. Finally, we provide a comparative evaluation on ChatGPT against existing state-of-the-art quadruple extraction models based on four public datasets and highlight some important findings regarding the capability boundaries of ChatGPT in the quadruple extraction.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 23 of its 43 references that are in the map. First posted on arXiv 10 Oct 2023.

Builds on

23 of 43 references.

References · 23

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  6. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  7. 2023ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPTcited by 250
  8. 2023Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERTcited by 155
  9. 2019Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysiscited by 123
  10. 2021Aspect Sentiment Quad Prediction as Paraphrase Generationcited by 100
  11. 2021A Unified Generative Framework for Aspect-Based Sentiment Analysiscited by 97
  12. 2023Is ChatGPT a Good Sentiment Analyzer? A Preliminary Studycited by 96
11 more
  1. 2020Position-Aware Tagging for Aspect Sentiment Triplet Extractioncited by 91
  2. 2021A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysiscited by 62
  3. 2021Learning Span-Level Interactions for Aspect Sentiment Triplet Extractioncited by 60
  4. 2018A Unified Model for Opinion Target Extraction and Target Sentiment Predictioncited by 56
  5. 2023Zero-shot Temporal Relation Extraction with ChatGPTcited by 53
  6. 2019An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysiscited by 52
  7. 2018CAN: Constrained Attention Networks for Multi-Aspect Sentiment Analysiscited by 21
  8. 2022Instruction Tuning for Few-Shot Aspect-Based Sentiment Analysiscited by 16
  9. 2022A Span-level Bidirectional Network for Aspect Sentiment Triplet Extractioncited by 12
  10. 2022UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuningcited by 9
  11. 2020A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysiscited by 7

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024Large Language Models Meet NLP: A Surveycited by 103
  2. 2024A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysiscited by 5
  3. 2024Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Predictioncited by 4
  4. 2024LLM-Cure: LLM-based Competitor User Review Analysis for Feature Enhancementcited by 4
  5. 2025STAR: Stepwise Task Augmentation with Relation Learning for Aspect Sentiment Quad Predictioncited by 2
  6. 2025Targeted Distillation for Sentiment Analysiscited by 1