mlsanityData to 14 Oct 2026

From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models

arXiv 2503.20715 ↗First posted 26 Mar 2025cs.CLcited by 1

On the map: Synthetic data and self-improvement for LLMs → LLM synthetic data generation

Abstract (arXiv)

This study examines the performance of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA), with a focus on implicit aspect extraction in a novel domain. Using a synthetic sports feedback dataset, we evaluate open-weight LLMs' ability to extract aspect-polarity pairs and propose a metric to facilitate the evaluation of aspect extraction with generative models. Our findings highlight both the potential and limitations of LLMs in the ABSA task.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in LLM synthetic data generation, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 15 of its 54 references that are in the map. First posted on arXiv 26 Mar 2025.

Builds on

15 of 54 references.

References · 15

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  4. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  5. 2018Datasheets for Datasetscited by 1,386
  6. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  7. 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 449
  8. 2022Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionalscited by 191
  9. 2020Relational Graph Attention Network for Aspect-based Sentiment Analysiscited by 104
  10. 2023LLMs Accelerate Annotation for Medical Information Extractioncited by 77
  11. 2023SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learningcited by 38
  12. 2024If in a Crowdsourced Data Annotation Pipeline, a GPT-4cited by 38
3 more
  1. 2023In-Context Learning for Text Classification with Many Labelscited by 35
  2. 2023InstructABSA: Instruction Learning for Aspect Based Sentiment Analysiscited by 23
  3. 2022A Survey on Aspect-Based Sentiment Classificationcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026LASQ: A Low-resource Aspect-based Sentiment Quadruple Extraction Datasetcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Multi-Domain ABSA Conversation Dataset Generation via LLMs for Real-World Evaluation and Model Comparison
  2. 2026Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs
  3. 2023On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training
  4. 2025Balanced Training Data Augmentation for Aspect-Based Sentiment Analysis
  5. 2024Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models
  6. 2021Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis
  7. 2024Enhancing Long-Range Dependency with State Space Model and Kolmogorov-Arnold Networks for Aspect-Based Sentiment Analysis
  8. 2024DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis