mlsanityData to 7 Oct 2026

Large language models for aspect-based sentiment analysis

arXiv 2310.18025 ↗First posted 27 Oct 2023cs.CL cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) offer unprecedented text completion capabilities. As general models, they can fulfill a wide range of roles, including those of more specialized models. We assess the performance of GPT-4 and GPT-3.5 in zero shot, few shot and fine-tuned settings on the aspect-based sentiment analysis (ABSA) task. Fine-tuned GPT-3.5 achieves a state-of-the-art F1 score of 83.8 on the joint aspect term extraction and polarity classification task of the SemEval-2014 Task 4, improving upon InstructABSA [@scaria_instructabsa_2023] by 5.7%. However, this comes at the price of 1000 times more model parameters and thus increased inference cost. We discuss the the cost-performance trade-offs of different models, and analyze the typical errors that they make. Our results also indicate that detailed prompts improve performance in zero-shot and few-shot settings but are not necessary for fine-tuned models. This evidence is relevant for practioners that are faced with the choice of prompt engineering versus fine-tuning when using LLMs for ABSA.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 7 of its 11 references that are in the map. First posted on arXiv 27 Oct 2023.

Builds on

7 of 11 references.

References · 7

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  6. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  7. 2022A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challengescited by 61

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 5; 2026: 5.

17 papers.

Sort:

By area:

  1. 2024Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thoughtcited by 34
  2. 2025A Vision for Auto Research with LLM Agentscited by 17
  3. 2024Reasoning Elicitation in Language Models via Counterfactual Feedbackcited by 14
  4. 2025Large Language Models for Subjective Language Understanding: A Surveycited by 9
  5. 2024Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Modelscited by 8
  6. 2024A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysiscited by 5
  7. 2025Balanced Training Data Augmentation for Aspect-Based Sentiment Analysiscited by 5
  8. 2024Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Modelscited by 4
  9. 2025Large Language Models Enhanced by Plug and Play Syntactic Knowledge for Aspect-based Sentiment Analysiscited by 3
  10. 2025LLaMA-Based Models for Aspect-Based Sentiment Analysiscited by 3
  11. 2024DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysiscited by 2
  12. 2024In-Context Learning for Long-Context Sentiment Analysis on Infrastructure Project Opinionscited by 1
5 more
  1. 2026Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMscited by 0
  2. 2026LLM-as-an-Annotator: Training Lightweight Models with LLM-Annotated Examples for Aspect Sentiment Tuple Predictioncited by 0
  3. 2026LASQ: A Low-resource Aspect-based Sentiment Quadruple Extraction Datasetcited by 0
  4. 2026Zero-Shot to Full-Resource: Cross-lingual Transfer Strategies for Aspect-Based Sentiment Analysiscited by 0
  5. 2026Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysiscited by 0