---
title: "Tree-CoT-RT — paper by Zhang et al. (2026)"
description: "The paper addresses Aspect Sentiment Quad Prediction (ASQP), which extracts aspect, category, opinion and sentiment from… 48 references."
authors: ["Hao Zhang", "Jiahao Wang", "Zhenke Duan", "Xin Yin", "Haichuan Hu", "Hualong Chen", "Suyi", "Congqing He", "Yike Tan", "Yu-N Cheah"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.806/"
doi: "10.18653/v1/2026.findings-acl.806"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-tree-cot-rt-explainable-multi/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-tree-cot-rt-explainable-multi/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/54/) / Tree-CoT-RT: An Explainable Multi-Path Tree-Guided Chain-of-Thought and Reinforcement Learning Framework for Aspect Sentiment Quad Prediction

# Tree-CoT-RT: An Explainable Multi-Path Tree-Guided Chain-of-Thought and Reinforcement Learning Framework for Aspect Sentiment Quad Prediction

**Authors:** [Hao Zhang](https://md.research.elamur.ai/free/en/authors/hao-zhang/), [Jiahao Wang](https://md.research.elamur.ai/free/en/authors/jiahao-wang/), Zhenke Duan, [Xin Yin](https://md.research.elamur.ai/free/en/authors/xin-yin/), Haichuan Hu, Hualong Chen, Suyi, Congqing He, Yike Tan and Yu-N Cheah · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.806/) · [PDF](https://aclanthology.org/2026.findings-acl.806.pdf) · [DOI 10.18653/v1/2026.findings-acl.806](https://doi.org/10.18653/v1/2026.findings-acl.806) · [OpenAlex](https://openalex.org/W7166812682)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary

The paper addresses Aspect Sentiment Quad Prediction (ASQP), which extracts aspect, category, opinion and sentiment from a sentence. The task is hardest when the aspect or the opinion is never stated outright, and current systems tend to be opaque and unreliable in those cases. The authors' framework, Tree-CoT-RT, splits quadruples into four explicit/implicit types and gives each type its own tree-shaped reasoning template. These templates prompt LLMs to write step-by-step justifications alongside the predicted quadruples.

Because the resulting chains differ in quality, a GRPO-based reinforcement learning step scores and filters them with a hand-crafted, rule-based reward. The retained chains are then used to fine-tune the model. At inference time, several reasoning paths are sampled and combined by voting.

On REST-ACOS and LAPTOP-ACOS, the method beats strong baselines, and the largest gains appear on implicit aspects and opinions. This suggests that structured, interpretable reasoning supervision helps fine-grained sentiment analysis. Code and data are publicly released.

## Key points

- The four quad types are EAEO, EAIO, IAEO and IAIO. For each type and sentence, K=10 Tree-CoT chains were generated with Gemini 2.5 Pro and ChatGPT-4. These chains were used for LoRA-based tree-supervised fine-tuning (tSFT) of Qwen2.5-7B-Instruct.
- The GRPO step samples groups of G=10 chains. Its reward combines four weighted terms: label consistency, path validity, implicit alignment and diversity.
- The best variant, Tree-CoT-RT-Qwen2.5-32B, reaches an F1 of 71.22 on REST and 50.25 on LAPTOP. The S²IT-32B baseline scores 67.37 and 46.70. Tree-CoT-RT with Qwen2.5-7B (69.50 / 49.10) and LLaMA3-8B (68.42 / 48.38) also beats this baseline.
- In the ablations on the Qwen variant, removing both the reasoning-chain generation and the RL steps causes the largest drop: −5.87 F1 on REST and −3.95 on LAPTOP. Among the reward terms, dropping the implicit-signal term hurts most, costing about 5 F1 points on each dataset.
- The stated limitations are that the method handles only single sentences and text-only input, and that the reward is designed by hand. Code is available at github.com/sydmou/ASQP-Tree-CoT-RT.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 598 works · 191,226 citations
- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 224 works · 13,587 citations
- [Hong Kong Polytechnic University](https://md.research.elamur.ai/free/en/universities/hong-kong-polytechnic-university/) — University, Hong Kong, China · 106 works · 5,190 citations
- [Capital Medical University](https://md.research.elamur.ai/free/en/universities/capital-medical-university/) — University, Beijing, China · 2 works · 7 citations
- [Zhongnan University of Economics and Law](https://md.research.elamur.ai/free/en/universities/zhongnan-university-of-economics-and-law/) — University, Wuhan, China · 2 works · 3 citations
- [Huzhou Normal University](https://md.research.elamur.ai/free/en/universities/huzhou-normal-university/) — University, Huzhou, China · 2 works

Also on the byline: [Universiti Sains Malaysia](https://ror.org/02rgb2k63).

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 1,035 works

## Cite

Cite as: Hao Zhang, Jiahao Wang, Zhenke Duan, Xin Yin, Haichuan Hu, Hualong Chen, Suyi, Congqing He, Yike Tan and Yu-N Cheah. 2026. Tree-CoT-RT: An Explainable Multi-Path Tree-Guided Chain-of-Thought and Reinforcement Learning Framework for Aspect Sentiment Quad Prediction. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhang2026tree,
  title = {{Tree-CoT-RT: An Explainable Multi-Path Tree-Guided Chain-of-Thought and Reinforcement Learning Framework for Aspect Sentiment Quad Prediction}},
  author = {Hao Zhang, Jiahao Wang, Zhenke Duan, Xin Yin, Haichuan Hu, Hualong Chen, Suyi, Congqing He, Yike Tan and Yu-N Cheah},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.806},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.806}
}
```

- [← previous Tree-Based Interview Topic Guidance for Collecting Target Information under Adaptive Topic continuation/switching](https://md.research.elamur.ai/free/en/papers/nagasawa-2026-tree-based-interview-topic-guidance/)
- [next → Tree-Notebook: A Context-Aware Agent with Tree Search and Entropy-Aware Data Shadow for Interactive Data Science](https://md.research.elamur.ai/free/en/papers/qiu-2026-tree-notebook-context-aware-agent/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/54/)

## References

48 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Xiaoyi Bao, Z Wang, Xiaotong Jiang, Rong Xiao, and Shoushan Li. 2022. Aspect-based sentiment analysis with opinion tree generation. [find](https://scholar.google.com/scholar?q=Xiaoyi+Bao%2C+Z+Wang%2C+Xiaotong+Jiang%2C+Rong+Xiao%2C+and+Shoushan+Li%2E+2022%2E+Aspect%2Dbased+sentiment+analysis+with+opinion+tree+generation%2E)
2. Jiahao Bu, Lei Ren, Shuang Zheng, Yang Yang, Jingang Wang, Fuzheng Zhang, and Wei Wu. 2021. Asap: A chinese review dataset towards aspect category sentiment analysis and rating prediction. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Lingui… [find](https://scholar.google.com/scholar?q=Jiahao+Bu%2C+Lei+Ren%2C+Shuang+Zheng%2C+Yang+Yang%2C+Jingang+Wang%2C+Fuzheng+Zhang%2C+and+Wei+Wu%2E+2021%2E+Asap%3A+A+chinese+review+dataset+towards+aspect+category+sentiment+analysis+and+rating+prediction%2E+In+Proceedi)
3. Hongjie Cai, Yaofeng Tu, Xiangsheng Zhou, Jianfei Yu, and Rui Xia. 2020. Aspect-category based sentiment analysis with hierarchical graph convolutional network. In Proceedings of the 28th international conference on computational linguistics, pages 833– 843. [find](https://scholar.google.com/scholar?q=Hongjie+Cai%2C+Yaofeng+Tu%2C+Xiangsheng+Zhou%2C+Jianfei+Yu%2C+and+Rui+Xia%2E+2020%2E+Aspect%2Dcategory+based+sentiment+analysis+with+hierarchical+graph+convolutional+network%2E+In+Proceedings+of+the+28th+internationa)
4. Hongjie Cai, Rui Xia, and Jianfei Yu. 2021. [Aspect-category-opinion-sentiment quadruple extraction with implicit aspects and opinions](https://md.research.elamur.ai/free/en/papers/cai-2021-aspect-category-opinion-sentiment-quadruple/). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing…
5. Bingfeng Chen, Chenjie Qiu, Yifeng Xie, Boyan Xu, Ruichu Cai, and Zhifeng Hao. 2025. S 2 IT: Stepwise syntax integration tuning for large language models in aspect sentiment quad prediction. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 6799–6806, Albuquerque, New M… [find](https://scholar.google.com/scholar?q=Bingfeng+Chen%2C+Chenjie+Qiu%2C+Yifeng+Xie%2C+Boyan+Xu%2C+Ruichu+Cai%2C+and+Zhifeng+Hao%2E+2025%2E+S+2+IT%3A+Stepwise+syntax+integration+tuning+for+large+language+models+in+aspect+sentiment+quad+prediction%2E+In+Findin)
6. Shaowei Chen, Yu Wang, Jie Liu, and Yuelin Wang. 2021. Bidirectional machine reading comprehension for aspect sentiment triplet extraction. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 12666–12674. [find](https://scholar.google.com/scholar?q=Shaowei+Chen%2C+Yu+Wang%2C+Jie+Liu%2C+and+Yuelin+Wang%2E+2021%2E+Bidirectional+machine+reading+comprehension+for+aspect+sentiment+triplet+extraction%2E+In+Proceedings+of+the+AAAI+conference+on+artificial+intellig)
7. Zheng Chu, Jingchang Chen, Qianglong Chen, Weijiang Yu, Tao He, Haotian Wang, Weihua Peng, Ming Liu, Bing Qin, and Ting Liu. 2024. [Navigate through enigmatic labyrinth a survey of chain of thought reasoning: Advances, frontiers and future](https://md.research.elamur.ai/free/en/papers/chu-2023-navigate-through-enigmatic-labyrinth-survey/). In Proceedings of the 62nd Annual Meeting of the Association…
8. DeepSeek. 2024. Deepseek r1: Generalist language agent with reasoning and action. [https://deepseekcoder.github.io/blog/deepseek-r1](https://deepseekcoder.github.io/blog/deepseek-r1). Accessed: 2025-05-19. [↗](https://deepseekcoder.github.io/blog/deepseek-r1)
9. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [BERT: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
10. Zhifang Fan, Zhen Wu, Xinyu Dai, Shujian Huang, and Jiajun Chen. 2019. [Target-oriented opinion words extraction with target-fused neural sequence labeling](https://md.research.elamur.ai/free/en/papers/fan-2019-target-oriented-opinion-words-extraction/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologie…
11. Hao Fei, Bobo Li, Qian Liu, Lidong Bing, Fei Li, and Tat-Seng Chua. 2023. Reasoning implicit sentiment with chain-of-thought prompting. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1171–1182, Toronto, Canada. Association f… [find](https://scholar.google.com/scholar?q=Hao+Fei%2C+Bobo+Li%2C+Qian+Liu%2C+Lidong+Bing%2C+Fei+Li%2C+and+Tat%2DSeng+Chua%2E+2023%2E+Reasoning+implicit+sentiment+with+chain%2Dof%2Dthought+prompting%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for)
12. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
13. Cao Duy Hoang, Quang Vinh Dinh, and Ngoc Hong Tran. 2022. Aspect-category-opinion-sentiment extraction using generative transformer model. In 2022 RIVF International Conference on Computing and Communication Technologies (RIVF), pages 1–6. IEEE. [find](https://scholar.google.com/scholar?q=Cao+Duy+Hoang%2C+Quang+Vinh+Dinh%2C+and+Ngoc+Hong+Tran%2E+2022%2E+Aspect%2Dcategory%2Dopinion%2Dsentiment+extraction+using+generative+transformer+model%2E+In+2022+RIVF+International+Conference+on+Computing+and+Commun)
14. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022a. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). ICLR, 1(2):3.
15. Mengting Hu, Yinhao Bai, Yike Wu, Zhen Zhang, Liqi Zhang, Hang Gao, Shiwan Zhao, and Minlie Huang. 2023. Uncertainty-aware unlikelihood learning improves generative aspect sentiment quad prediction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 13481–13494, Toronto, C… [find](https://scholar.google.com/scholar?q=Mengting+Hu%2C+Yinhao+Bai%2C+Yike+Wu%2C+Zhen+Zhang%2C+Liqi+Zhang%2C+Hang+Gao%2C+Shiwan+Zhao%2C+and+Minlie+Huang%2E+2023%2E+Uncertainty%2Daware+unlikelihood+learning+improves+generative+aspect+sentiment+quad+prediction%2E+I)
16. Mengting Hu, Yike Wu, Hang Gao, Yinhao Bai, and Shiwan Zhao. 2022b. Improving aspect sentiment quad prediction via template-order data augmentation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7889–7900, Abu Dhabi, United Arab Emirates. Associatio… [find](https://scholar.google.com/scholar?q=Mengting+Hu%2C+Yike+Wu%2C+Hang+Gao%2C+Yinhao+Bai%2C+and+Shiwan+Zhao%2E+2022b%2E+Improving+aspect+sentiment+quad+prediction+via+template%2Dorder+data+augmentation%2E+In+Proceedings+of+the+2022+Conference+on+Empirical+)
17. Jieyong Kim, Ryang Heo, Yongsik Seo, SeongKu Kang, Jinyoung Yeo, and Dongha Lee. 2024. Self-consistent reasoning-based aspect-sentiment quad prediction with extract-then-assign strategy. In Findings of the Association for Computational Linguistics ACL 2024, pages 7295–7303, Bangkok, Thailand and vir… [find](https://scholar.google.com/scholar?q=Jieyong+Kim%2C+Ryang+Heo%2C+Yongsik+Seo%2C+SeongKu+Kang%2C+Jinyoung+Yeo%2C+and+Dongha+Lee%2E+2024%2E+Self%2Dconsistent+reasoning%2Dbased+aspect%2Dsentiment+quad+prediction+with+extract%2Dthen%2Dassign+strategy%2E+In+Findings+o)
18. Takeshi Kojima, Shixiang (Shane) Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). In Advances in Neural Information Processing Systems, volume 35, pages 22199–22213. Curran Associates, Inc.
19. Google DeepMind. 2024. Gemini 1.5 technical report. [https://deepmind.google/technologies/](https://deepmind.google/technologies/) gemini/\#gemini-15. Accessed: 2025-05-19. [↗](https://deepmind.google/technologies/)
20. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. [BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/). In Proceedings of the 58th Annual Meeting of the…
21. Zhibin Gou, Qingyan Guo, and Yujiu Yang. 2023. MvP: Multi-view prompting improves aspect sentiment tuple prediction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4380–4397, Toronto, Canada. Association for Computational Lin… [find](https://scholar.google.com/scholar?q=Zhibin+Gou%2C+Qingyan+Guo%2C+and+Yujiu+Yang%2E+2023%2E+MvP%3A+Multi%2Dview+prompting+improves+aspect+sentiment+tuple+prediction%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Association+for+Computational+Ling)
22. Jian Liu, Zhiyang Teng, Leyang Cui, Hanmeng Liu, and Yue Zhang. 2021. Solving aspect category sentiment analysis as a text generation task. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4406–4416, Online and Punta Cana, Dominican Republic. Associati… [find](https://scholar.google.com/scholar?q=Jian+Liu%2C+Zhiyang+Teng%2C+Leyang+Cui%2C+Hanmeng+Liu%2C+and+Yue+Zhang%2E+2021%2E+Solving+aspect+category+sentiment+analysis+as+a+text+generation+task%2E+In+Proceedings+of+the+2021+Conference+on+Empirical+Methods+i)
23. Jiangming Liu and Yue Zhang. 2017. Attention modeling for targeted sentiment. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 572–577, Valencia, Spain. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Jiangming+Liu+and+Yue+Zhang%2E+2017%2E+Attention+modeling+for+targeted+sentiment%2E+In+Proceedings+of+the+15th+Conference+of+the+European+Chapter+of+the+Association+for+Computational+Linguistics%3A+Volume+2%2C+)
24. Yequan Wang, Minlie Huang, Xiaoyan Zhu, and Li Zhao. 2016. [Attention-based LSTM for aspect-level sentiment classification](https://md.research.elamur.ai/free/en/papers/wang-2016-attention-based-lstm-aspect-level/). In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 606–615, Austin, Texas. Association for Computational Linguistics.
25. Yue Mao, Yi Shen, Jingchao Yang, Xiaoying Zhu, and Longjun Cai. 2022. Seq2Path: Generating sentiment tuples as paths of a tree. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2215–2225, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yue+Mao%2C+Yi+Shen%2C+Jingchao+Yang%2C+Xiaoying+Zhu%2C+and+Longjun+Cai%2E+2022%2E+Seq2Path%3A+Generating+sentiment+tuples+as+paths+of+a+tree%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2022%2C+)
26. Zengzhi Wang, Rui Xia, and Jianfei Yu. 2024. Unified absa via annotation-decoupled multi-task instruction tuning. IEEE Transactions on Knowledge and Data Engineering. [find](https://scholar.google.com/scholar?q=Zengzhi+Wang%2C+Rui+Xia%2C+and+Jianfei+Yu%2E+2024%2E+Unified+absa+via+annotation%2Ddecoupled+multi%2Dtask+instruction+tuning%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering%2E)
27. Yue Mao, Yi Shen, Chao Yu, and Longjun Cai. 2021. A joint training dual-mrc framework for aspect based sentiment analysis. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 13543–13551. [find](https://scholar.google.com/scholar?q=Yue+Mao%2C+Yi+Shen%2C+Chao+Yu%2C+and+Longjun+Cai%2E+2021%2E+A+joint+training+dual%2Dmrc+framework+for+aspect+based+sentiment+analysis%2E+In+Proceedings+of+the+AAAI+conference+on+artificial+intelligence%2C+volume+35%2C+)
28. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv:2303.08774.
29. Preprint, OpenAI. 2025. Introducing GPT-5. [https://openai.com/index/introducing-gpt-5/](https://openai.com/index/introducing-gpt-5/). Accessed: 2026-01-06. [↗](https://openai.com/index/introducing-gpt-5/)
30. Haiyun Peng, Lu Xu, Lidong Bing, Fei Huang, Wei Lu, and Luo Si. 2020. Knowing what, how and why: A near complete solution for aspect-based sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):8600–8607. [find](https://scholar.google.com/scholar?q=Haiyun+Peng%2C+Lu+Xu%2C+Lidong+Bing%2C+Fei+Huang%2C+Wei+Lu%2C+and+Luo+Si%2E+2020%2E+Knowing+what%2C+how+and+why%3A+A+near+complete+solution+for+aspect%2Dbased+sentiment+analysis%2E+Proceedings+of+the+AAAI+Conference+on+Art)
31. Joseph Peper and Lu Wang. 2022. Generative aspect-based sentiment analysis with contrastive learning and expressive structure. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6089–6095, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Joseph+Peper+and+Lu+Wang%2E+2022%2E+Generative+aspect%2Dbased+sentiment+analysis+with+contrastive+learning+and+expressive+structure%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2022%2C)
32. Guang Qiu, Bing Liu, Jiajun Bu, and Chun Chen. 2011. [Opinion word expansion and target extraction through double propagation](https://md.research.elamur.ai/free/en/papers/qiu-2011-opinion-word-expansion-target-extraction/). Computational linguistics, 37(1):9–27.
33. Qwen. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). https://arxiv.org/abs/2505.09388. Preprint, arXiv:2505.09388. Accessed: 2026-01-06. [↗](https://arxiv.org/abs/2505.09388)
34. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. [Exploring the limits of transfer learning with a unified text-to-text transformer](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of Machine Learning Research, 21(140):1–67.
35. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al. 2024. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300.
36. Hai Wan, Yufei Yang, Jianfeng Du, Yanan Liu, Kunxun Qi, and Jeff Z. Pan. 2020. Target-aspect-sentiment joint detection for aspect-based sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):9122–9129. [find](https://scholar.google.com/scholar?q=Hai+Wan%2C+Yufei+Yang%2C+Jianfeng+Du%2C+Yanan+Liu%2C+Kunxun+Qi%2C+and+Jeff+Z%2E+Pan%2E+2020%2E+Target%2Daspect%2Dsentiment+joint+detection+for+aspect%2Dbased+sentiment+analysis%2E+Proceedings+of+the+AAAI+Conference+on+Artifi)
37. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Advances in Neural Information Processing Systems, volume 35, pages 24824–24837. Curran Associates, Inc.
38. Chao Wu, Qingyu Xiong, Hualing Yi, Yang Yu, Qiwu Zhu, Min Gao, and Jie Chen. 2021. Multiple-element joint detection for aspect-based sentiment analysis. Knowledge-Based Systems, 223:107073. [find](https://scholar.google.com/scholar?q=Chao+Wu%2C+Qingyu+Xiong%2C+Hualing+Yi%2C+Yang+Yu%2C+Qiwu+Zhu%2C+Min+Gao%2C+and+Jie+Chen%2E+2021%2E+Multiple%2Delement+joint+detection+for+aspect%2Dbased+sentiment+analysis%2E+Knowledge%2DBased+Systems%2C+223%3A107073%2E)
39. H. Xiong, Z. Yan, C. Wu, et al. 2023. Bart-based contrastive and retrospective network for aspect-category-opinion-sentiment quadruple extraction. International Journal of Machine Learning and Cybernetics, 14:3243–3255. [find](https://scholar.google.com/scholar?q=H%2E+Xiong%2C+Z%2E+Yan%2C+C%2E+Wu%2C+et+al%2E+2023%2E+Bart%2Dbased+contrastive+and+retrospective+network+for+aspect%2Dcategory%2Dopinion%2Dsentiment+quadruple+extraction%2E+International+Journal+of+Machine+Learning+and+Cyberne)
40. Lu Xu, Hao Li, Wei Lu, and Lidong Bing. 2020. [Position-aware tagging for aspect sentiment triplet extraction](https://md.research.elamur.ai/free/en/papers/xu-2020-position-aware-tagging-aspect-sentiment/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2339–2349, Online. Association for Computational Linguistics.
41. Yichun Yin, Furu Wei, Li Dong, Kaimeng Xu, Ming Zhang, and Ming Zhou. 2016. Unsupervised word and dependency path embeddings for aspect term extraction. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pages 2979–2985. [find](https://scholar.google.com/scholar?q=Yichun+Yin%2C+Furu+Wei%2C+Li+Dong%2C+Kaimeng+Xu%2C+Ming+Zhang%2C+and+Ming+Zhou%2E+2016%2E+Unsupervised+word+and+dependency+path+embeddings+for+aspect+term+extraction%2E+In+Proceedings+of+the+Twenty%2DFifth+Internationa)
42. Hao Zhang, Yu-N Cheah, Osamah Mohammed Alyasiri, and Jieyu An. 2023a. A survey on aspect-based sentiment quadruple extraction with implicit aspects and opinions. Research Square, Preprint. [find](https://scholar.google.com/scholar?q=Hao+Zhang%2C+Yu%2DN+Cheah%2C+Osamah+Mohammed+Alyasiri%2C+and+Jieyu+An%2E+2023a%2E+A+survey+on+aspect%2Dbased+sentiment+quadruple+extraction+with+implicit+aspects+and+opinions%2E+Research+Square%2C+Preprint%2E)
43. Hao Zhang, Yu-N Cheah, Osamah Mohammed Alyasiri, and Jieyu An. 2024a. Exploring aspect-based sentiment quadruple extraction with implicit aspects, opinions, and chatgpt: a comprehensive survey. Artificial Intelligence Review, 57(2):17. [find](https://scholar.google.com/scholar?q=Hao+Zhang%2C+Yu%2DN+Cheah%2C+Osamah+Mohammed+Alyasiri%2C+and+Jieyu+An%2E+2024a%2E+Exploring+aspect%2Dbased+sentiment+quadruple+extraction+with+implicit+aspects%2C+opinions%2C+and+chatgpt%3A+a+comprehensive+survey%2E+Artifi)
44. Hao Zhang, Yu-N Cheah, Congqing He, and Feifan Yi. 2024b. An instruction tuning-based contrastive learning framework for aspect sentiment quad prediction with implicit aspects and opinions. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7698–7714, Miami, Florida, USA… [find](https://scholar.google.com/scholar?q=Hao+Zhang%2C+Yu%2DN+Cheah%2C+Congqing+He%2C+and+Feifan+Yi%2E+2024b%2E+An+instruction+tuning%2Dbased+contrastive+learning+framework+for+aspect+sentiment+quad+prediction+with+implicit+aspects+and+opinions%2E+In+Finding)
45. Wenxuan Zhang, Yang Deng, Xin Li, Yifei Yuan, Lidong Bing, and Wai Lam. 2021a. [Aspect sentiment quad prediction as paraphrase generation](https://md.research.elamur.ai/free/en/papers/zhang-2021-aspect-sentiment-quad-prediction-as/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9209– 9219, Online and Punta Cana, Dominican Republic. Associatio…
46. Wenyuan Zhang, Xinghua Zhang, Shiyao Cui, Kun Huang, Xuebin Wang, and Tingwen Liu. 2024c. Adaptive data augmentation for aspect sentiment quad prediction. In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 11176–11180. [find](https://scholar.google.com/scholar?q=Wenyuan+Zhang%2C+Xinghua+Zhang%2C+Shiyao+Cui%2C+Kun+Huang%2C+Xuebin+Wang%2C+and+Tingwen+Liu%2E+2024c%2E+Adaptive+data+augmentation+for+aspect+sentiment+quad+prediction%2E+In+ICASSP+2024+%2D+2024+IEEE+International+Conf)
47. Yice Zhang, Yifan Yang, Meng Li, Bin Liang, Shiwei Chen, and Ruifeng Xu. 2023b. Target-to-source augmentation for aspect sentiment triplet extraction. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12165–12177, Singapore. Association for Computationa… [find](https://scholar.google.com/scholar?q=Yice+Zhang%2C+Yifan+Yang%2C+Meng+Li%2C+Bin+Liang%2C+Shiwei+Chen%2C+and+Ruifeng+Xu%2E+2023b%2E+Target%2Dto%2Dsource+augmentation+for+aspect+sentiment+triplet+extraction%2E+In+Proceedings+of+the+2023+Conference+on+Empirica)
48. He Zhao, Longtao Huang, Rong Zhang, Quan Lu, and Hui Xue. 2020. Spanmlt: A span-based multi-task learning framework for pair-wise aspect and opinion terms extraction. In Proceedings of the 58th annual meeting of the association for computational linguistics, pages 3239–3248. [find](https://scholar.google.com/scholar?q=He+Zhao%2C+Longtao+Huang%2C+Rong+Zhang%2C+Quan+Lu%2C+and+Hui+Xue%2E+2020%2E+Spanmlt%3A+A+span%2Dbased+multi%2Dtask+learning+framework+for+pair%2Dwise+aspect+and+opinion+terms+extraction%2E+In+Proceedings+of+the+58th+annual)

*Updated 2 November 2026*