---
title: "Resource-Limited Joint Multimodal Sentiment Reasoning and"
description: "The authors define a task, JMSRC, in which one small MLLM must both produce an explanatory reasoning chain and predict… 59 references."
authors: ["Haonan Shangguan", "Xiaocui Yang", "Shi Feng", "Daling Wang", "Yifei Zhang", "Feiliang Ren", "Ge Yu"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.784/"
doi: "10.18653/v1/2026.findings-acl.784"
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/shangguan-2026-resource-limited-joint-multimodal-sentiment/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shangguan-2026-resource-limited-joint-multimodal-sentiment/)

[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/16/) / Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation

# Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation

**Authors:** Haonan Shangguan, [Xiaocui Yang](https://md.research.elamur.ai/free/en/authors/xiaocui-yang/), [Shi Feng](https://md.research.elamur.ai/free/en/authors/shi-feng/), [Daling Wang](https://md.research.elamur.ai/free/en/authors/daling-wang/), [Yifei Zhang](https://md.research.elamur.ai/free/en/authors/yifei-zhang/), Feiliang Ren and [Ge Yu](https://md.research.elamur.ai/free/en/authors/ge-yu/) · **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.784/) · [PDF](https://aclanthology.org/2026.findings-acl.784.pdf) · [DOI 10.18653/v1/2026.findings-acl.784](https://doi.org/10.18653/v1/2026.findings-acl.784) · [OpenAlex](https://openalex.org/W7166850175)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
The paper tackles multimodal sentiment analysis of text-image posts when only a small model can be deployed. Existing approaches typically use large or closed MLLMs to inject knowledge or reasoning into a classifier, but they do not give a lightweight model its own reasoning ability. The authors define a task, JMSRC, in which one small MLLM must both produce an explanatory reasoning chain and predict the sentiment label. They propose MulCoT-RD, which distills reasoning through three tiers. First, a strong teacher (e.g., GPT-4o-mini) is guided by structured CoT prompts to build a reasoning dataset. Next, a medium-sized open-source assistant model is trained with multi-task learning; it then generates additional data and supplies soft labels. Finally, a 3B student learns from both hard and soft labels. Across four coarse- and fine-grained datasets, the 3B student performs strongly, generalizes well and produces interpretable explanations. This shows that explainable multimodal sentiment analysis can be practical without heavy compute.

## Key points
- **Two-stage reasoning data construction.** In stage 1, the teacher predicts labels without seeing them, and only rationales for correct predictions are kept. In stage 2, misclassified samples are re-prompted with the gold label so the teacher explains the correct answer. Adaptive retry control is used throughout.
- **Fixed reasoning format.** Each rationale contains text analysis, image analysis, conflict resolution, a final conclusion and the prediction (positive/neutral/negative). Fine-grained (MASC) inputs also include an aspect term.
- **Why an assistant model.** It is a medium-sized open-source MLLM trained jointly on classification and reasoning. It supplies soft labels that a closed teacher cannot provide and helps with the shortage of reasoning data.
- **Student training and motivation.** The student has only 3B parameters and is optimized on hard labels plus temperature-scaled soft labels from the assistant. The authors cite prior evidence that MLLMs of ≤3B parameters reason weakly with CoT on their own.
- **Limitations.** Reasoning quality was judged only with automatic metrics (n-gram overlap and embedding cosine similarity), with no large-scale human evaluation. Generating data with the teacher is costly. Code and a demo are available at github.com/123sghn/MulCoT-RD.

*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

- [Northeastern University](https://md.research.elamur.ai/free/en/universities/northeastern-university-cn/) — University, Shenyang, China · 42 works · 1,940 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 870 works

🧭 Topics (3): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works · [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 972 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 657 works

## Cite

Cite as: Haonan Shangguan, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Feiliang Ren and Ge Yu. 2026. Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation. 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{shangguan2026resource,
  title = {{Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation}},
  author = {Haonan Shangguan, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Feiliang Ren and Ge Yu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.784},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.784}
}
```

- [← previous RES2 at IMPOLS 2026: Implicit Content Classification via Span-Awareness, Hierarchical Multi-Task Learning and Synthetic Data](https://md.research.elamur.ai/free/en/papers/spezia-2026-res2-impols-2026-implicit-content/)
- [next → Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms](https://md.research.elamur.ai/free/en/papers/wang-2026-rethinking-scale-deployment-trade-offs/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/16/)

## References

59 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Shahin Amiriparian, Lukas Christ, Alexander Kathan, Maurice Gerczuk, Niklas Müller, Steffen Klug, Lukas Stappen, Andreas König, Erik Cambria, Björn W Schuller, and 1 others. 2024. The muse 2024 multimodal sentiment analysis challenge: Social perception and humor recognition. In Proceedings of the 5t… [find](https://scholar.google.com/scholar?q=Shahin+Amiriparian%2C+Lukas+Christ%2C+Alexander+Kathan%2C+Maurice+Gerczuk%2C+Niklas+M%C3%BCller%2C+Steffen+Klug%2C+Lukas+Stappen%2C+Andreas+K%C3%B6nig%2C+Erik+Cambria%2C+Bj%C3%B6rn+W+Schuller%2C+and+1+others%2E+2024%2E+The+muse+2024+multim)
2. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — [Qwen2.5-VL Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/)
3. Satanjeev Banerjee and Alon Lavie. 2005. [Meteor: An automatic metric for mt evaluation with improved correlation with human judgments](https://md.research.elamur.ai/free/en/papers/banerjee-2005-meteor-automatic-metric-mt-evaluation/). In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and/or summarization, pages 65–72.
4. Dan Biderman, Jacob Portes, Jose Javier Gonzalez Ortiz, Mansheej Paul, Philip Greengard, Connor Jennings, Daniel King, Sam Havens, Vitaliy Chiley, Jonathan Frankle, and 1 others. 2024. Lora learns less and forgets less. arXiv preprint arXiv:2405.09673. [find](https://scholar.google.com/scholar?q=Dan+Biderman%2C+Jacob+Portes%2C+Jose+Javier+Gonzalez+Ortiz%2C+Mansheej+Paul%2C+Philip+Greengard%2C+Connor+Jennings%2C+Daniel+King%2C+Sam+Havens%2C+Vitaliy+Chiley%2C+Jonathan+Frankle%2C+and+1+others%2E+2024%2E+Lora+learns+les)
5. Yifan Chen, Kuntao Li, Weixing Mai, Qiaofeng Wu, Yun Xue, and Fenghuan Li. 2024. D2r: Dual-branch dynamic routing network for multimodal sentiment detection. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 3536–3547. [find](https://scholar.google.com/scholar?q=Yifan+Chen%2C+Kuntao+Li%2C+Weixing+Mai%2C+Qiaofeng+Wu%2C+Yun+Xue%2C+and+Fenghuan+Li%2E+2024%2E+D2r%3A+Dual%2Dbranch+dynamic+routing+network+for+multimodal+sentiment+detection%2E+In+Proceedings+of+the+2024+Conference+on+E)
6. Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, and Alexander Hauptmann. 2024. Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning. Advances in Neural Information Processing Systems, 37:110805–110853. [find](https://scholar.google.com/scholar?q=Zebang+Cheng%2C+Zhi%2DQi+Cheng%2C+Jun%2DYan+He%2C+Kai+Wang%2C+Yuxiang+Lin%2C+Zheng+Lian%2C+Xiaojiang+Peng%2C+and+Alexander+Hauptmann%2E+2024%2E+Emotion%2Dllama%3A+Multimodal+emotion+recognition+and+reasoning+with+instruction+t)
7. Li Chenglin, Qianglong Chen, Liangyue Li, Caiyu Wang, Feng Tao, Yicheng Li, Zulong Chen, and Yin Zhang. 2024. Mixed distillation helps smaller language models reason better. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 1673–1690. [find](https://scholar.google.com/scholar?q=Li+Chenglin%2C+Qianglong+Chen%2C+Liangyue+Li%2C+Caiyu+Wang%2C+Feng+Tao%2C+Yicheng+Li%2C+Zulong+Chen%2C+and+Yin+Zhang%2E+2024%2E+Mixed+distillation+helps+smaller+language+models+reason+better%2E+In+Findings+of+the+Associa)
8. Yanqi Dai, Zebin You, Dong Jing, Yutian Luo, Nanyi Fei, Guoxing Yang, and Zhiwu Lu. 2024. Cotbal: Comprehensive task balancing for multi-task visual instruction tuning. arXiv preprint arXiv:2403.04343. — [arXiv:2403.04343](https://arxiv.org/abs/2403.04343) [find](https://scholar.google.com/scholar?q=Yanqi+Dai%2C+Zebin+You%2C+Dong+Jing%2C+Yutian+Luo%2C+Nanyi+Fei%2C+Guoxing+Yang%2C+and+Zhiwu+Lu%2E+2024%2E+Cotbal%3A+Comprehensive+task+balancing+for+multi%2Dtask+visual+instruction+tuning%2E+arXiv+preprint+arXiv%3A2403%2E04343)
9. Yuxian Gu, Li Dong, Furu Wei, and Minlie Huang. 2023. [Minillm: Knowledge distillation of large language models](https://md.research.elamur.ai/free/en/papers/gu-2023-minillm-policy-distillation-large-language/). arXiv preprint arXiv:2306.08543.
10. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. [Distilling the knowledge in a neural network](https://md.research.elamur.ai/free/en/papers/hinton-2015-distilling-knowledge-neural-network/). arXiv preprint arXiv:1503.02531.
11. Jian Huang, Jianhua Tao, Bin Liu, Zheng Lian, and Mingyue Niu. 2020. Multimodal transformer fusion for continuous emotion recognition. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 3507– 3511. IEEE. [find](https://scholar.google.com/scholar?q=Jian+Huang%2C+Jianhua+Tao%2C+Bin+Liu%2C+Zheng+Lian%2C+and+Mingyue+Niu%2E+2020%2E+Multimodal+transformer+fusion+for+continuous+emotion+recognition%2E+In+ICASSP+2020%2D2020+IEEE+International+Conference+on+Acoustics%2C+S)
12. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv preprint arXiv:2410.21276.
13. Xincheng Ju, Dong Zhang, Rong Xiao, Junhui Li, Shoushan Li, Min Zhang, and Guodong Zhou. 2021. Joint multi-modal aspect-sentiment analysis with auxiliary cross-modal relation detection. In Proceedings of the 2021 conference on empirical methods in natural language processing, pages 4395–4405. [find](https://scholar.google.com/scholar?q=Xincheng+Ju%2C+Dong+Zhang%2C+Rong+Xiao%2C+Junhui+Li%2C+Shoushan+Li%2C+Min+Zhang%2C+and+Guodong+Zhou%2E+2021%2E+Joint+multi%2Dmodal+aspect%2Dsentiment+analysis+with+auxiliary+cross%2Dmodal+relation+detection%2E+In+Proceedings)
14. Zaid Khan and Yun Fu. 2021. Exploiting bert for multimodal target sentiment classification through input space translation. In Proceedings of the 29th ACM international conference on multimedia, pages 3034– 3042. [find](https://scholar.google.com/scholar?q=Zaid+Khan+and+Yun+Fu%2E+2021%2E+Exploiting+bert+for+multimodal+target+sentiment+classification+through+input+space+translation%2E+In+Proceedings+of+the+29th+ACM+international+conference+on+multimedia%2C+pages)
15. Junho Kim, Jun-Hyung Park, Mingyu Lee, Wing-Lam Mok, Joon-Young Choi, and SangKeun Lee. 2022. Tutoring helps students learn better: Improving knowledge distillation for bert with tutor network. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7371–7382… [find](https://scholar.google.com/scholar?q=Junho+Kim%2C+Jun%2DHyung+Park%2C+Mingyu+Lee%2C+Wing%2DLam+Mok%2C+Joon%2DYoung+Choi%2C+and+SangKeun+Lee%2E+2022%2E+Tutoring+helps+students+learn+better%3A+Improving+knowledge+distillation+for+bert+with+tutor+network%2E+In+Pro)
16. Yan Li, Xiangyuan Lan, Haifeng Chen, Ke Lu, and Dongmei Jiang. 2025a. Multimodal pear chain-of-thought reasoning for multimodal sentiment analysis. ACM Transactions on Multimedia Computing, Communications and Applications, 20(9):1–23. [find](https://scholar.google.com/scholar?q=Yan+Li%2C+Xiangyuan+Lan%2C+Haifeng+Chen%2C+Ke+Lu%2C+and+Dongmei+Jiang%2E+2025a%2E+Multimodal+pear+chain%2Dof%2Dthought+reasoning+for+multimodal+sentiment+analysis%2E+ACM+Transactions+on+Multimedia+Computing%2C+Communicat)
17. Yuetai Li, Xiang Yue, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Bhaskar Ramasubramanian, and Radha Poovendran. 2025b. Small models struggle to learn from strong reasoners. arXiv preprint arXiv:2502.12143. [find](https://scholar.google.com/scholar?q=Yuetai+Li%2C+Xiang+Yue%2C+Zhangchen+Xu%2C+Fengqing+Jiang%2C+Luyao+Niu%2C+Bill+Yuchen+Lin%2C+Bhaskar+Ramasubramanian%2C+and+Radha+Poovendran%2E+2025b%2E+Small+models+struggle+to+learn+from+strong+reasoners%2E+arXiv+prepri)
18. Zhen Li, Bing Xu, Conghui Zhu, and Tiejun Zhao. 2022. Clmlf: A contrastive learning and multi-layer fusion method for multimodal sentiment detection. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2282–2294. [find](https://scholar.google.com/scholar?q=Zhen+Li%2C+Bing+Xu%2C+Conghui+Zhu%2C+and+Tiejun+Zhao%2E+2022%2E+Clmlf%3A+A+contrastive+learning+and+multi%2Dlayer+fusion+method+for+multimodal+sentiment+detection%2E+In+Findings+of+the+Association+for+Computational+L)
19. Chin-Yew Lin. 2004. [Rouge: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text summarization branches out, pages 74–81.
20. Yan Ling, Jianfei Yu, and Rui Xia. 2022. Vision-language pre-training for multimodal aspect-based sentiment analysis. arXiv preprint arXiv:2204.07955. [find](https://scholar.google.com/scholar?q=Yan+Ling%2C+Jianfei+Yu%2C+and+Rui+Xia%2E+2022%2E+Vision%2Dlanguage+pre%2Dtraining+for+multimodal+aspect%2Dbased+sentiment+analysis%2E+arXiv+preprint+arXiv%3A2204%2E07955%2E)
21. Wuchao Liu, Wengen Li, Yu-Ping Ruan, Yulou Shu, Juntao Chen, Yina Li, Caili Yu, Yichao Zhang, Jihong Guan, and Shuigeng Zhou. 2024. Weakly correlated multimodal sentiment analysis: New dataset and topic-oriented model. IEEE Transactions on Affective Computing, 15(4):2070–2082. [find](https://scholar.google.com/scholar?q=Wuchao+Liu%2C+Wengen+Li%2C+Yu%2DPing+Ruan%2C+Yulou+Shu%2C+Juntao+Chen%2C+Yina+Li%2C+Caili+Yu%2C+Yichao+Zhang%2C+Jihong+Guan%2C+and+Shuigeng+Zhou%2E+2024%2E+Weakly+correlated+multimodal+sentiment+analysis%3A+New+dataset+and+top)
22. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2017%2E+Decoupled+weight+decay+regularization%2E+arXiv+preprint+arXiv%3A1711%2E05101%2E)
23. Lucie Charlotte Magister, Jonathan Mallinson, Jakub Adamek, Eric Malmi, and Aliaksei Severyn. 2022. [Teaching small language models to reason](https://md.research.elamur.ai/free/en/papers/magister-2023-teaching-small-language-models-reason/). arXiv preprint arXiv:2212.08410.
24. Ayush Kumar and Jithendra Vepa. 2020. Gated mechanism for attention based multi modal sentiment analysis. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 4477–4481. IEEE. [find](https://scholar.google.com/scholar?q=Ayush+Kumar+and+Jithendra+Vepa%2E+2020%2E+Gated+mechanism+for+attention+based+multi+modal+sentiment+analysis%2E+In+ICASSP+2020%2D2020+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%28)
25. Muhammad Arslan Manzoor, Sarah Albarri, Ziting Xian, Zaiqiao Meng, Preslav Nakov, and Shangsong Liang. 2023. Multimodality representation learning: A survey on evolution, pretraining and its applications. ACM Transactions on Multimedia Computing, Communications and Applications, 20(3):1–34. [find](https://scholar.google.com/scholar?q=Muhammad+Arslan+Manzoor%2C+Sarah+Albarri%2C+Ziting+Xian%2C+Zaiqiao+Meng%2C+Preslav+Nakov%2C+and+Shangsong+Liang%2E+2023%2E+Multimodality+representation+learning%3A+A+survey+on+evolution%2C+pretraining+and+its+applicati)
26. Hojae Lee, Junho Kim, and SangKeun Lee. 2024. Mentor-kd: Making small language models better multi-step reasoners. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17643–17658. [find](https://scholar.google.com/scholar?q=Hojae+Lee%2C+Junho+Kim%2C+and+SangKeun+Lee%2E+2024%2E+Mentor%2Dkd%3A+Making+small+language+models+better+multi%2Dstep+reasoners%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natural+Language+Proces)
27. Ning Pang, Wansen Wu, Yue Hu, Kai Xu, Quanjun Yin, and Long Qin. 2024. Enhancing multimodal sentiment analysis via learning from large language model. In 2024 IEEE International Conference on Multimedia and Expo (ICME), pages 1–6. IEEE. [find](https://scholar.google.com/scholar?q=Ning+Pang%2C+Wansen+Wu%2C+Yue+Hu%2C+Kai+Xu%2C+Quanjun+Yin%2C+and+Long+Qin%2E+2024%2E+Enhancing+multimodal+sentiment+analysis+via+learning+from+large+language+model%2E+In+2024+IEEE+International+Conference+on+Multimed)
28. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2015. [A diversity-promoting objective function for neural conversation models](https://md.research.elamur.ai/free/en/papers/li-2016-diversity-promoting-objective-function-neural/). arXiv preprint arXiv:1510.03055.
29. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
30. Liunian Harold Li, Jack Hessel, Youngjae Yu, Xiang Ren, Kai-Wei Chang, and Yejin Choi. 2023. [Symbolic chain-of-thought distillation: Small models can also" think" step-by-step](https://md.research.elamur.ai/free/en/papers/li-2023-symbolic-chain-thought-distillation-small/). arXiv preprint arXiv:2306.14050.
31. Tianshuo Peng, Zuchao Li, Ping Wang, Lefei Zhang, and Hai Zhao. 2024. A novel energy based model mechanism for multi-modal aspect-based sentiment analysis. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18869– 18878. [find](https://scholar.google.com/scholar?q=Tianshuo+Peng%2C+Zuchao+Li%2C+Ping+Wang%2C+Lefei+Zhang%2C+and+Hai+Zhao%2E+2024%2E+A+novel+energy+based+model+mechanism+for+multi%2Dmodal+aspect%2Dbased+sentiment+analysis%2E+In+Proceedings+of+the+AAAI+Conference+on+Art)
32. Pol G Recasens, Ferran Agullo, Yue Zhu, Chen Wang, Eun Kyung Lee, Olivier Tardieu, Jordi Torres, and Josep Ll Berral. 2025. Mind the memory gap: Unveiling gpu bottlenecks in large-batch llm inference. arXiv preprint arXiv:2503.08311. [find](https://scholar.google.com/scholar?q=Pol+G+Recasens%2C+Ferran+Agullo%2C+Yue+Zhu%2C+Chen+Wang%2C+Eun+Kyung+Lee%2C+Olivier+Tardieu%2C+Jordi+Torres%2C+and+Josep+Ll+Berral%2E+2025%2E+Mind+the+memory+gap%3A+Unveiling+gpu+bottlenecks+in+large%2Dbatch+llm+inference%2E)
33. Nils Reimers and Iryna Gurevych. 2019. [Sentence-bert: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). arXiv preprint arXiv:1908.10084.
34. Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108. [find](https://scholar.google.com/scholar?q=Victor+Sanh%2C+Lysandre+Debut%2C+Julien+Chaumond%2C+and+Thomas+Wolf%2E+2019%2E+Distilbert%2C+a+distilled+version+of+bert%3A+smaller%2C+faster%2C+cheaper+and+lighter%2E+arXiv+preprint+arXiv%3A1910%2E01108%2E)
35. OpenBMB MiniCPM-o Team. 2025. Minicpm-o 2.6: A gpt-4o level mllm for vision, speech, and multimodal live streaming on your phone. [find](https://scholar.google.com/scholar?q=OpenBMB+MiniCPM%2Do+Team%2E+2025%2E+Minicpm%2Do+2%2E6%3A+A+gpt%2D4o+level+mllm+for+vision%2C+speech%2C+and+multimodal+live+streaming+on+your+phone%2E)
36. Wenbin Wang, Liang Ding, Li Shen, Yong Luo, Han Hu, and Dacheng Tao. 2024. Wisdom: Improving multimodal sentiment analysis by fusing contextual world knowledge. In Proceedings of the 32nd ACM international conference on multimedia, pages 2282– 2291. [find](https://scholar.google.com/scholar?q=Wenbin+Wang%2C+Liang+Ding%2C+Li+Shen%2C+Yong+Luo%2C+Han+Hu%2C+and+Dacheng+Tao%2E+2024%2E+Wisdom%3A+Improving+multimodal+sentiment+analysis+by+fusing+contextual+world+knowledge%2E+In+Proceedings+of+the+32nd+ACM+internat)
37. Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, and Furu Wei. 2020a. Minilmv2: Multi-head self-attention relation distillation for compressing pretrained transformers. arXiv preprint arXiv:2012.15828. [find](https://scholar.google.com/scholar?q=Wenhui+Wang%2C+Hangbo+Bao%2C+Shaohan+Huang%2C+Li+Dong%2C+and+Furu+Wei%2E+2020a%2E+Minilmv2%3A+Multi%2Dhead+self%2Dattention+relation+distillation+for+compressing+pretrained+transformers%2E+arXiv+preprint+arXiv%3A2012%2E15828)
38. Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020b. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in neural information processing systems, 33:5776–5788. [find](https://scholar.google.com/scholar?q=Wenhui+Wang%2C+Furu+Wei%2C+Li+Dong%2C+Hangbo+Bao%2C+Nan+Yang%2C+and+Ming+Zhou%2E+2020b%2E+Minilm%3A+Deep+self%2Dattention+distillation+for+task%2Dagnostic+compression+of+pre%2Dtrained+transformers%2E+Advances+in+neural+infor)
39. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 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/). Advances in neural information processing systems, 35:24824– 24837.
40. Yiwei Wei, Shaozu Yuan, Ruosong Yang, Lei Shen, Zhangmeizhi Li, Longbiao Wang, and Meng Chen. 2023. Tackling modality heterogeneity with multi-view calibration network for multimodal sentiment detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volu… [find](https://scholar.google.com/scholar?q=Yiwei+Wei%2C+Shaozu+Yuan%2C+Ruosong+Yang%2C+Lei+Shen%2C+Zhangmeizhi+Li%2C+Longbiao+Wang%2C+and+Meng+Chen%2E+2023%2E+Tackling+modality+heterogeneity+with+multi%2Dview+calibration+network+for+multimodal+sentiment+detecti)
41. Taiqiang Wu, Chaofan Tao, Jiahao Wang, Runming Yang, Zhe Zhao, and Ngai Wong. 2025. [Rethinking kullback-leibler divergence in knowledge distillation for large language models](https://md.research.elamur.ai/free/en/papers/wu-2025-rethinking-kullback-leibler-divergence-knowledge/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 5737–5755.
42. Zhiyu Wu, Xiaokang Chen, Zizheng Pan, Xingchao Liu, Wen Liu, Damai Dai, Huazuo Gao, Yiyang Ma, Chengyue Wu, Bingxuan Wang, and 1 others. 2024. [Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding](https://md.research.elamur.ai/free/en/papers/wu-2024-deepseek-vl2-mixture-experts/). arXiv preprint arXiv:2412.10302.
43. Luwei Xiao, Xingjiao Wu, Shuwen Yang, Junjie Xu, Jie Zhou, and Liang He. 2023. Cross-modal fine-grained alignment and fusion network for multimodal aspect-based sentiment analysis. Information Processing & Management, 60(6):103508. [find](https://scholar.google.com/scholar?q=Luwei+Xiao%2C+Xingjiao+Wu%2C+Shuwen+Yang%2C+Junjie+Xu%2C+Jie+Zhou%2C+and+Liang+He%2E+2023%2E+Cross%2Dmodal+fine%2Dgrained+alignment+and+fusion+network+for+multimodal+aspect%2Dbased+sentiment+analysis%2E+Information+Process)
44. Nan Xu. 2017. Analyzing multimodal public sentiment based on hierarchical semantic attentional network. In 2017 IEEE international conference on intelligence and security informatics (ISI), pages 152–154. IEEE. [find](https://scholar.google.com/scholar?q=Nan+Xu%2E+2017%2E+Analyzing+multimodal+public+sentiment+based+on+hierarchical+semantic+attentional+network%2E+In+2017+IEEE+international+conference+on+intelligence+and+security+informatics+%28ISI%29%2C+pages+152%E2%80%93)
45. Nan Xu and Wenji Mao. 2017. Multisentinet: A deep semantic network for multimodal sentiment analysis. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pages 2399–2402. [find](https://scholar.google.com/scholar?q=Nan+Xu+and+Wenji+Mao%2E+2017%2E+Multisentinet%3A+A+deep+semantic+network+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+the+2017+ACM+on+Conference+on+Information+and+Knowledge+Management%2C+pages+2399%E2%80%932)
46. Nan Xu, Wenji Mao, and Guandan Chen. 2018. A co-memory network for multimodal sentiment analysis. In The 41st international ACM SIGIR conference on research & development in information retrieval, pages 929–932. [find](https://scholar.google.com/scholar?q=Nan+Xu%2C+Wenji+Mao%2C+and+Guandan+Chen%2E+2018%2E+A+co%2Dmemory+network+for+multimodal+sentiment+analysis%2E+In+The+41st+international+ACM+SIGIR+conference+on+research+%26+development+in+information+retrieval%2C+pag)
47. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025a. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
48. Hao Yang, Yanyan Zhao, Yang Wu, Shilong Wang, Tian Zheng, Hongbo Zhang, Zongyang Ma, Wanxiang Che, and Bing Qin. 2024. Large language models meet text-centric multimodal sentiment analysis: A survey. arXiv preprint arXiv:2406.08068. — [arXiv:2406.08068](https://arxiv.org/abs/2406.08068) [find](https://scholar.google.com/scholar?q=Hao+Yang%2C+Yanyan+Zhao%2C+Yang+Wu%2C+Shilong+Wang%2C+Tian+Zheng%2C+Hongbo+Zhang%2C+Zongyang+Ma%2C+Wanxiang+Che%2C+and+Bing+Qin%2E+2024%2E+Large+language+models+meet+text%2Dcentric+multimodal+sentiment+analysis%3A+A+survey%2E+)
49. Li Yang, Jin-Cheon Na, and Jianfei Yu. 2022. Cross-modal multitask transformer for end-to-end multimodal aspect-based sentiment analysis. Information Processing & Management, 59(5):103038. [find](https://scholar.google.com/scholar?q=Li+Yang%2C+Jin%2DCheon+Na%2C+and+Jianfei+Yu%2E+2022%2E+Cross%2Dmodal+multitask+transformer+for+end%2Dto%2Dend+multimodal+aspect%2Dbased+sentiment+analysis%2E+Information+Processing+%26+Management%2C+59%285%29%3A103038%2E)
50. Xiaocui Yang, Shi Feng, Yifei Zhang, and Daling Wang. 2021. Multimodal sentiment detection based on multi-channel graph neural networks. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processi… [find](https://scholar.google.com/scholar?q=Xiaocui+Yang%2C+Shi+Feng%2C+Yifei+Zhang%2C+and+Daling+Wang%2E+2021%2E+Multimodal+sentiment+detection+based+on+multi%2Dchannel+graph+neural+networks%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+fo)
51. Yang Yang, Hongpeng Pan, Qing-Yuan Jiang, Yi Xu, and Jinhui Tang. 2025b. Learning to rebalance multimodal optimization by adaptively masking subnetworks. IEEE Transactions on Pattern Analysis and Machine Intelligence. [find](https://scholar.google.com/scholar?q=Yang+Yang%2C+Hongpeng+Pan%2C+Qing%2DYuan+Jiang%2C+Yi+Xu%2C+and+Jinhui+Tang%2E+2025b%2E+Learning+to+rebalance+multimodal+optimization+by+adaptively+masking+subnetworks%2E+IEEE+Transactions+on+Pattern+Analysis+and+Mach)
52. Yuyang Ye, Zhi Zheng, Yishan Shen, Tianshu Wang, Hengruo Zhang, Peijun Zhu, Runlong Yu, Kai Zhang, and Hui Xiong. 2025. Harnessing multimodal large language models for multimodal sequential recommendation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 13069– 1307… [find](https://scholar.google.com/scholar?q=Yuyang+Ye%2C+Zhi+Zheng%2C+Yishan+Shen%2C+Tianshu+Wang%2C+Hengruo+Zhang%2C+Peijun+Zhu%2C+Runlong+Yu%2C+Kai+Zhang%2C+and+Hui+Xiong%2E+2025%2E+Harnessing+multimodal+large+language+models+for+multimodal+sequential+recommenda)
53. Jianfei Yu and Jing Jiang. 2019. Adapting bert for target-oriented multimodal sentiment classification. IJCAI. [find](https://scholar.google.com/scholar?q=Jianfei+Yu+and+Jing+Jiang%2E+2019%2E+Adapting+bert+for+target%2Doriented+multimodal+sentiment+classification%2E+IJCAI%2E)
54. Jianfei Yu, Jing Jiang, and Rui Xia. 2019. Entity-sensitive attention and fusion network for entity-level multimodal sentiment classification. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28:429–439. [find](https://scholar.google.com/scholar?q=Jianfei+Yu%2C+Jing+Jiang%2C+and+Rui+Xia%2E+2019%2E+Entity%2Dsensitive+attention+and+fusion+network+for+entity%2Dlevel+multimodal+sentiment+classification%2E+IEEE%2FACM+Transactions+on+Audio%2C+Speech%2C+and+Language+Proc)
55. Haoyu Zhang, Yu Wang, Guanghao Yin, Kejun Liu, Yuanyuan Liu, and Tianshu Yu. 2023. Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 756–767. [find](https://scholar.google.com/scholar?q=Haoyu+Zhang%2C+Yu+Wang%2C+Guanghao+Yin%2C+Kejun+Liu%2C+Yuanyuan+Liu%2C+and+Tianshu+Yu%2E+2023%2E+Learning+language%2Dguided+adaptive+hyper%2Dmodality+representation+for+multimodal+sentiment+analysis%2E+In+Proceedings+of+)
56. Yazhou Zhang, Prayag Tiwari, Lu Rong, Rui Chen, No-joom A AlNajem, and M Shamim Hossain. 2022. Affective interaction: Attentive representation learning for multi-modal sentiment classification. ACM Transactions on Multimedia Computing, Communications and Applications, 18(3s):1–23. [find](https://scholar.google.com/scholar?q=Yazhou+Zhang%2C+Prayag+Tiwari%2C+Lu+Rong%2C+Rui+Chen%2C+No%2Djoom+A+AlNajem%2C+and+M+Shamim+Hossain%2E+2022%2E+Affective+interaction%3A+Attentive+representation+learning+for+multi%2Dmodal+sentiment+classification%2E+ACM+Tr)
57. Yiqun Zhang, Xiaocui Yang, Xiaobai Li, Siyuan Yu, Yi Luan, Shi Feng, Daling Wang, and Yifei Zhang. 2024. Psydraw: A multi-agent multimodal system for mental health screening in left-behind children. arXiv preprint arXiv:2412.14769. — [arXiv:2412.14769](https://arxiv.org/abs/2412.14769) [find](https://scholar.google.com/scholar?q=Yiqun+Zhang%2C+Xiaocui+Yang%2C+Xiaobai+Li%2C+Siyuan+Yu%2C+Yi+Luan%2C+Shi+Feng%2C+Daling+Wang%2C+and+Yifei+Zhang%2E+2024%2E+Psydraw%3A+A+multi%2Dagent+multimodal+system+for+mental+health+screening+in+left%2Dbehind+children%2E+a)
58. Ru Zhou, Wenya Guo, Xumeng Liu, Shenglong Yu, Ying Zhang, and Xiaojie Yuan. 2023. Aom: Detecting aspect-oriented information for multimodal aspect-based sentiment analysis. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8184–8196. [find](https://scholar.google.com/scholar?q=Ru+Zhou%2C+Wenya+Guo%2C+Xumeng+Liu%2C+Shenglong+Yu%2C+Ying+Zhang%2C+and+Xiaojie+Yuan%2E+2023%2E+Aom%3A+Detecting+aspect%2Doriented+information+for+multimodal+aspect%2Dbased+sentiment+analysis%2E+In+Findings+of+the+Associat)
59. Linlin Zhu, Heli Sun, Qunshu Gao, Yuze Liu, and Liang He. 2025. Aspect enhancement and text simplification in multimodal aspect-based sentiment analysis for multi-aspect and multi-sentiment scenarios. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 1683–1691. [find](https://scholar.google.com/scholar?q=Linlin+Zhu%2C+Heli+Sun%2C+Qunshu+Gao%2C+Yuze+Liu%2C+and+Liang+He%2E+2025%2E+Aspect+enhancement+and+text+simplification+in+multimodal+aspect%2Dbased+sentiment+analysis+for+multi%2Daspect+and+multi%2Dsentiment+scenarios%2E)

*Updated 31 October 2026*