# DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis

arXiv: https://arxiv.org/abs/2603.16546 · HTML: https://mlsanity.com/paper/2603.16546/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 60 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors](https://mlsanity.com/paper/2405.07940/) (2024)
- [Aspect Sentiment Quad Prediction as Paraphrase Generation](https://mlsanity.com/paper/2110.00796/) (2021)
- [Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2406.09136/) (2024)
- [AgentReview: Exploring Peer Review Dynamics with LLM Agents](https://mlsanity.com/paper/2406.12708/) (2024)
- [MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction](https://mlsanity.com/paper/2305.12627/) (2023)
- [ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics](https://mlsanity.com/paper/2509.00496/) (2025)
- [Satirical News Detection and Analysis using Attention Mechanism and Linguistic Features](https://mlsanity.com/paper/1709.01189/) (2017)
- [Human-in-the-Loop Schema Induction](https://mlsanity.com/paper/2302.13048/) (2023)
- [Probabilistic Soundness Guarantees in LLM Reasoning Chains](https://mlsanity.com/paper/2507.12948/) (2025)
- [Self-Consistent Reasoning-based Aspect-Sentiment Quad Prediction with Extract-Then-Assign Strategy](https://mlsanity.com/paper/2403.00354/) (2024)
- [Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty](https://mlsanity.com/paper/2412.09572/) (2024)
- [Challenges for Open-domain Targeted Sentiment Analysis](https://mlsanity.com/paper/2204.06893/) (2022)
- [Overhearing LLM Agents: A Survey, Taxonomy, and Roadmap](https://mlsanity.com/paper/2509.16325/) (2025)
- [Document-Level Supervision for Multi-Aspect Sentiment Analysis Without Fine-grained Labels](https://mlsanity.com/paper/2310.06940/) (2023)
- [A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design](https://mlsanity.com/paper/2508.10899/) (2025)

## Abstract (arXiv)

Aspect-Based Sentiment Intensity Analysis (ABSIA) has garnered increasing attention, though research largely focuses on domain-specific, sentence-level settings. In contrast, document-level ABSIA--particularly in addressing complex tasks like extracting Aspect-Category-Opinion-Sentiment-Intensity (ACOSI) tuples--remains underexplored. In this work, we introduce DanceHA, a multi-agent framework designed for open-ended, document-level ABSIA with informal writing styles. DanceHA has two main components: Dance, which employs a divide-and-conquer strategy to decompose the long-context ABSIA task into smaller, manageable sub-tasks for collaboration among specialized agents; and HA, Human-AI collaboration for annotation. We release Inf-ABSIA, a multi-domain document-level ABSIA dataset featuring fine-grained and high-accuracy labels from DanceHA. Extensive experiments demonstrate the effectiveness of our agentic framework and show that the multi-agent knowledge in DanceHA can be effectively transferred into student models. Our results highlight the importance of the overlooked informal styles in ABSIA, as they often intensify opinions tied to specific aspects.