mlsanityData to 7 Oct 2026

Label-Consistent Data Generation for Aspect-Based Sentiment Analysis Using LLM Agents

arXiv 2602.16379 ↗First posted 18 Feb 2026cs.CLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

We propose an agentic data augmentation method for Aspect-Based Sentiment Analysis (ABSA) that uses iterative generation and verification to produce high quality synthetic training examples. To isolate the effect of agentic structure, we also develop a closely matched prompting-based baseline using the same model and instructions. Both methods are evaluated across three ABSA subtasks (Aspect Term Extraction (ATE), Aspect Sentiment Classification (ATSC), and Aspect Sentiment Pair Extraction (ASPE)), four SemEval datasets, and two encoder-decoder models: T5-Base and Tk-Instruct. Our results show that the agentic augmentation outperforms raw prompting in label preservation of the augmented data, especially when the tasks require aspect term generation. In addition, when combined with real data, agentic augmentation provides higher gains, consistently outperforming prompting-based generation. These benefits are most pronounced for T5-Base, while the more heavily pretrained Tk-Instruct exhibits smaller improvements. As a result, augmented data helps T5-Base achieve comparable performance with its counterpart.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 12 of its 19 references that are in the map. First posted on arXiv 18 Feb 2026.

Builds on

12 of 19 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay4 Apr
  2. 2024MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification28 Nov

Other references · 10

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  4. 2022ZeroGen: Efficient Zero-shot Learning via Dataset Generationcited by 209
  5. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  6. 2023Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitationscited by 96
  7. 2021AEDA: An Easier Data Augmentation Technique for Text Classificationcited by 67
  8. 2024Large Language Models have Intrinsic Self-Correction Abilitycited by 45
  9. 2020Adversarial Training for Aspect-Based Sentiment Analysis with BERTcited by 26
  10. 2023InstructABSA: Instruction Learning for Aspect Based Sentiment Analysiscited by 22

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis
  2. 2024DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis
  3. 2025Multi-Domain ABSA Conversation Dataset Generation via LLMs for Real-World Evaluation and Model Comparison
  4. 2023On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training
  5. 2025From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models
  6. 2026MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction
  7. 2025Are You Sure You're Positive? Consolidating Chain-of-Thought Agents with Uncertainty Quantification for Aspect-Category Sentiment Analysis
  8. 2026Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs