---
title: "Progressive Re-ranking for Multimodal Retrieval-Augmented"
description: "Knowledge-based visual question answering (VQA) asks about specific attributes of entities shown in images. 33 references."
authors: ["Zhu Min", "Yanchao Hao", "Jian Liu", "Shizhu He", "Xi Chen"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.2045/"
doi: "10.18653/v1/2026.findings-acl.2045"
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/min-2026-progressive-re-ranking-multimodal-retrieval/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/min-2026-progressive-re-ranking-multimodal-retrieval/)

[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/45/) / Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning

# Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning

**Authors:** Zhu Min, Yanchao Hao, [Jian Liu](https://md.research.elamur.ai/free/en/authors/jian-liu/), [Shizhu He](https://md.research.elamur.ai/free/en/authors/shizhu-he/) and [Xi Chen](https://md.research.elamur.ai/free/en/authors/xi-chen/) · **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.2045/) · [PDF](https://aclanthology.org/2026.findings-acl.2045.pdf) · [DOI 10.18653/v1/2026.findings-acl.2045](https://doi.org/10.18653/v1/2026.findings-acl.2045) · [OpenAlex](https://openalex.org/W7166831211)

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

## Summary
Knowledge-based visual question answering (VQA) asks about specific attributes of entities shown in images. Multimodal RAG for this task often fails because CLIP-style retrievers match images globally and miss fine-grained details. They can also return entities that look or read alike but lead the generator astray. The authors add a lightweight, stepwise re-ranking pipeline on top of CLIP-based coarse visual search over a Wikipedia corpus. First, a late-interaction model scores individual text sections of the candidate articles. Second, a multimodal reassessment step picks the single best section to pass to the generator. The re-ranker is trained with a curriculum of progressively harder negatives. Training starts with random articles, moves to sections from visually similar entities, and ends with misleading sections mined from the LLM's own decoding behaviour. On InfoSeek and Enc-VQA, the system reports state-of-the-art answer accuracy and competitive recall, with only modest extra retrieval time. This shows that carefully trained small re-rankers can substantially improve multimodal RAG.

## Key points
- **Pipeline:** CLIP-based visual search returns the top-20 articles. Fine-grained section re-ranking narrows these to the top-5 sections. Multimodal section reassessment, which uses Q-Former and F-Adapter components, then selects the top-1 section for generation.
- **Effect of negative sampling on InfoSeek (R@1, after stage two):**
  - random negatives: 53.5
  - visually similar entries: 57.6
  - generator-feedback hard negatives: 59.0
  - R@20 stays at 81.9 across all three strategies.
- **Size of the hard-negative set:** using 50k–200k samples gives R@1 between 58.32 and 59.14, with the best result at 100k samples and K=9. A small set of hard negatives therefore already yields most of the gain.
- **Comparison with EchoSight:**
  - VQA score: 50.32 vs. 41.8
  - R@1: 43.6 vs. 36.5
  - average retrieval time: 0.496 vs. 0.429
- **Limitations:** the overall upper bound depends on the quality of the initial CLIP retrieval. Hard-negative mining via LLM decoding-rank perturbation is costly and is done statically. The authors suggest dynamic selection, for example via reinforcement learning, as future work.

*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

- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations
- [Institute of Automation](https://md.research.elamur.ai/free/en/labs/institute-of-automation/) — Research institute, Beijing, China · 87 works · 14,883 citations
- [University of Science and Technology Beijing](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-beijing/) — University, Beijing, China · 10 works · 315 citations

📚 Shelves (6): [🖥️ 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

🧭 Topics (2): [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works · [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 552 works

## Cite

Cite as: Zhu Min, Yanchao Hao, Jian Liu, Shizhu He and Xi Chen. 2026. Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning. 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{min2026progressive,
  title = {{Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning}},
  author = {Zhu Min, Yanchao Hao, Jian Liu, Shizhu He and Xi Chen},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.2045},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.2045}
}
```

- [← previous Program-of-Thought Reveals LLM Abstraction Ceilings](https://md.research.elamur.ai/free/en/papers/zhou-2026-program-thought-reveals-llm-abstraction/)
- [next → Progressive Visual Refinement for Multi-modal Summarization](https://md.research.elamur.ai/free/en/papers/xiong-2026-progressive-visual-refinement-multi-modal/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/45/)

## References

33 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zitnick, and Devi Parikh. 2015. VQA: Visual question answering. In Proceedings of the IEEE international conference on computer vision, pages 2425–2433. [find](https://scholar.google.com/scholar?q=Stanislaw+Antol%2C+Aishwarya+Agrawal%2C+Jiasen+Lu%2C+Margaret+Mitchell%2C+Dhruv+Batra%2C+C+Lawrence+Zitnick%2C+and+Devi+Parikh%2E+2015%2E+VQA%3A+Visual+question+answering%2E+In+Proceedings+of+the+IEEE+international+confe)
2. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, and 1 others. 2023. [Qwen technical report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/). arXiv preprint arXiv:2309.16609.
3. Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. 2009. [Curriculum learning](https://md.research.elamur.ai/free/en/papers/bengio-2009-curriculum-learning/). In Proceedings of the 26th annual international conference on machine learning, pages 41–48.
4. Davide Caffagni, Federico Cocchi, Nicholas Moratelli, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, and Rita Cucchiara. 2024. Wiki-LLaVA: Hierarchical retrieval-augmented generation for multimodal LLMs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, p… [find](https://scholar.google.com/scholar?q=Davide+Caffagni%2C+Federico+Cocchi%2C+Nicholas+Moratelli%2C+Sara+Sarto%2C+Marcella+Cornia%2C+Lorenzo+Baraldi%2C+and+Rita+Cucchiara%2E+2024%2E+Wiki%2DLLaVA%3A+Hierarchical+retrieval%2Daugmented+generation+for+multimodal+LLM)
5. Yang Chen, Hexiang Hu, Yi Luan, Haitian Sun, Soravit Changpinyo, Alan Ritter, and Ming-Wei Chang. 2023. [Can pre-trained vision and language models answer visual information-seeking questions?](https://md.research.elamur.ai/free/en/papers/chen-2023-can-pre-trained-vision-language/) In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 14948–14968…
6. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, and 1 others. 2023. [PaLM: Scaling language modeling with pathways](https://md.research.elamur.ai/free/en/papers/chowdhery-2022-palm-scaling-language-modeling-pathways/). Journal of Machine Learning Research, 24(240):1–113.
7. Federico Cocchi, Nicholas Moratelli, Marcella Cornia, Lorenzo Baraldi, and Rita Cucchiara. 2025. Augmenting multimodal llms with self-reflective tokens for knowledge-based visual question answering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9199– 920… [find](https://scholar.google.com/scholar?q=Federico+Cocchi%2C+Nicholas+Moratelli%2C+Marcella+Cornia%2C+Lorenzo+Baraldi%2C+and+Rita+Cucchiara%2E+2025%2E+Augmenting+multimodal+llms+with+self%2Dreflective+tokens+for+knowledge%2Dbased+visual+question+answering%2E+I)
8. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, and 1 others. 2021. [An image is worth 16x16 words: Transformers for image recognition at scale](https://md.research.elamur.ai/free/en/papers/dosovitskiy-2020-image-worth-16x16-words-transformers/). International Conference on Le…
9. Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazaré, Maria Lomeli, Lucas Hosseini, and Hervé Jégou. 2024. [The Faiss library](https://md.research.elamur.ai/free/en/papers/douze-2024-faiss-library/). arXiv preprint arXiv:2401.08281.
10. Feng Gao, Qing Ping, Govind Thattai, Aishwarya Reganti, Ying Nian Wu, and Prem Natarajan. 2022. Transform-retrieve-generate: Natural language-centric outside-knowledge visual question answering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5067–5077. [find](https://scholar.google.com/scholar?q=Feng+Gao%2C+Qing+Ping%2C+Govind+Thattai%2C+Aishwarya+Reganti%2C+Ying+Nian+Wu%2C+and+Prem+Natarajan%2E+2022%2E+Transform%2Dretrieve%2Dgenerate%3A+Natural+language%2Dcentric+outside%2Dknowledge+visual+question+answering%2E+In+Pr)
11. Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. 2017. [Making the V in VQA matter: Elevating the role of image understanding in visual question answering](https://md.research.elamur.ai/free/en/papers/goyal-2016-making-v-vqa-matter-elevating/). In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6904–6913.
12. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 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. Liangke Gui, Borui Wang, Qiuyuan Huang, Alexander G Hauptmann, Yonatan Bisk, and Jianfeng Gao. 2022. Kat: A knowledge augmented transformer for vision-and-language. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Te… [find](https://scholar.google.com/scholar?q=Liangke+Gui%2C+Borui+Wang%2C+Qiuyuan+Huang%2C+Alexander+G+Hauptmann%2C+Yonatan+Bisk%2C+and+Jianfeng+Gao%2E+2022%2E+Kat%3A+A+knowledge+augmented+transformer+for+vision%2Dand%2Dlanguage%2E+In+Proceedings+of+the+2022+Conferen)
14. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, and 1 others. 2022. [LoRA: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). The Tenth International Conference on Learning Representations, 1(2):3.
15. Hexiang Hu, Yi Luan, Yang Chen, Urvashi Khandelwal, Mandar Joshi, Kenton Lee, Kristina Toutanova, and Ming-Wei Chang. 2023. Open-domain visual entity recognition: Towards recognizing millions of Wikipedia entities. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 120… [find](https://scholar.google.com/scholar?q=Hexiang+Hu%2C+Yi+Luan%2C+Yang+Chen%2C+Urvashi+Khandelwal%2C+Mandar+Joshi%2C+Kenton+Lee%2C+Kristina+Toutanova%2C+and+Ming%2DWei+Chang%2E+2023%2E+Open%2Ddomain+visual+entity+recognition%3A+Towards+recognizing+millions+of+Wikip)
16. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. [Unsupervised dense information retrieval with contrastive learning](https://md.research.elamur.ai/free/en/papers/izacard-2021-unsupervised-dense-information-retrieval-contrastive/). Transactions on Machine Learning Research.
17. Omar Khattab and Matei Zaharia. 2020. [ColBERT: Efficient and effective passage search via contextualized late interaction over BERT](https://md.research.elamur.ai/free/en/papers/khattab-2020-colbert-efficient-effective-passage/). In Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval, pages 39–48.
18. Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. [BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models](https://md.research.elamur.ai/free/en/papers/li-2023-blip-2-bootstrapping-language-image/). In International conference on machine learning, pages 19730–19742. PMLR.
19. Zihan Ling, Zhiyao Guo, Yixuan Huang, Yi An, Shuai Xiao, Jinsong Lan, Xiaoyong Zhu, and Bo Zheng. 2025. Mmkb-rag: A multi-modal knowledge-based retrieval-augmented generation framework. arXiv preprint arXiv:2504.10074. — [arXiv:2504.10074](https://arxiv.org/abs/2504.10074) [find](https://scholar.google.com/scholar?q=Zihan+Ling%2C+Zhiyao+Guo%2C+Yixuan+Huang%2C+Yi+An%2C+Shuai+Xiao%2C+Jinsong+Lan%2C+Xiaoyong+Zhu%2C+and+Bo+Zheng%2E+2025%2E+Mmkb%2Drag%3A+A+multi%2Dmodal+knowledge%2Dbased+retrieval%2Daugmented+generation+framework%2E+arXiv+preprint)
20. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. [Visual instruction tuning](https://md.research.elamur.ai/free/en/papers/liu-2023-visual-instruction-tuning/). Advances in neural information processing systems, 36:34892– 34916.
21. Kenneth Marino, Mohammad Rastegari, Ali Farhadi, and Roozbeh Mottaghi. 2019. OK-VQA: A visual question answering benchmark requiring external knowledge. In Proceedings of the IEEE/cvf conference on computer vision and pattern recognition, pages 3195–3204. [find](https://scholar.google.com/scholar?q=Kenneth+Marino%2C+Mohammad+Rastegari%2C+Ali+Farhadi%2C+and+Roozbeh+Mottaghi%2E+2019%2E+OK%2DVQA%3A+A+visual+question+answering+benchmark+requiring+external+knowledge%2E+In+Proceedings+of+the+IEEE%2Fcvf+conference+on+co)
22. Thomas Mensink, Jasper Uijlings, Lluis Castrejon, Arushi Goel, Felipe Cadar, Howard Zhou, Fei Sha, André Araujo, and Vittorio Ferrari. 2023. Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories. In Proceedings of the IEEE/CVF International Conference on Computer Vi… [find](https://scholar.google.com/scholar?q=Thomas+Mensink%2C+Jasper+Uijlings%2C+Lluis+Castrejon%2C+Arushi+Goel%2C+Felipe+Cadar%2C+Howard+Zhou%2C+Fei+Sha%2C+Andr%C3%A9+Araujo%2C+and+Vittorio+Ferrari%2E+2023%2E+Encyclopedic+VQA%3A+Visual+questions+about+detailed+propertie)
23. Jingyuan Qi, Zhiyang Xu, Rulin Shao, Yang Chen, Jin Di, Yu Cheng, Qifan Wang, and Lifu Huang. 2024. RoRA-VLM: Robust retrieval-augmented vision language models. arXiv preprint arXiv:2410.08876. — [arXiv:2410.08876](https://arxiv.org/abs/2410.08876) [find](https://scholar.google.com/scholar?q=Jingyuan+Qi%2C+Zhiyang+Xu%2C+Rulin+Shao%2C+Yang+Chen%2C+Jin+Di%2C+Yu+Cheng%2C+Qifan+Wang%2C+and+Lifu+Huang%2E+2024%2E+RoRA%2DVLM%3A+Robust+retrieval%2Daugmented+vision+language+models%2E+arXiv+preprint+arXiv%3A2410%2E08876%2E+%E2%80%94+%5BarX)
24. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and 1 others. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International conference on machine learning, pages 8748–8…
25. Dustin Schwenk, Apoorv Khandelwal, Christopher Clark, Kenneth Marino, and Roozbeh Mottaghi. 2022. [A-OKVQA: A benchmark for visual question answering using world knowledge](https://md.research.elamur.ai/free/en/papers/schwenk-2022-okvqa-benchmark-visual-question-answering/). In European conference on computer vision, pages 146–162. Springer.
26. Quan Sun, Yuxin Fang, Ledell Wu, Xinlong Wang, and Yue Cao. 2023. [EVA-CLIP: Improved training techniques for CLIP at scale](https://md.research.elamur.ai/free/en/papers/sun-2023-eva-clip-improved-training-techniques/). arXiv preprint arXiv:2303.15389.
27. Grant Van Horn, Elijah Cole, Sara Beery, Kimberly Wilber, Serge Belongie, and Oisin Mac Aodha. 2021. Benchmarking representation learning for natural world image collections. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12884–12893. [find](https://scholar.google.com/scholar?q=Grant+Van+Horn%2C+Elijah+Cole%2C+Sara+Beery%2C+Kimberly+Wilber%2C+Serge+Belongie%2C+and+Oisin+Mac+Aodha%2E+2021%2E+Benchmarking+representation+learning+for+natural+world+image+collections%2E+In+Proceedings+of+the+IEE)
28. Shaohan Wang, Licheng Zhang, Zheren Fu, and Zhendong Mao. 2025. Dacl-rag: Data augmentation strategy with curriculum learning for retrieval-augmented generation. arXiv preprint arXiv:2505.10493. — [arXiv:2505.10493](https://arxiv.org/abs/2505.10493) [find](https://scholar.google.com/scholar?q=Shaohan+Wang%2C+Licheng+Zhang%2C+Zheren+Fu%2C+and+Zhendong+Mao%2E+2025%2E+Dacl%2Drag%3A+Data+augmentation+strategy+with+curriculum+learning+for+retrieval%2Daugmented+generation%2E+arXiv+preprint+arXiv%3A2505%2E10493%2E+%E2%80%94+%5Bar)
29. Tobias Weyand, Andre Araujo, Bingyi Cao, and Jack Sim. 2020. Google landmarks dataset v2-a large-scale benchmark for instance-level recognition and retrieval. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2575–2584. [find](https://scholar.google.com/scholar?q=Tobias+Weyand%2C+Andre+Araujo%2C+Bingyi+Cao%2C+and+Jack+Sim%2E+2020%2E+Google+landmarks+dataset+v2%2Da+large%2Dscale+benchmark+for+instance%2Dlevel+recognition+and+retrieval%2E+In+Proceedings+of+the+IEEE%2FCVF+conference)
30. Yibin Yan and Weidi Xie. 2024. EchoSight: Advancing visual-language models with wiki knowledge. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 1538–1551. [find](https://scholar.google.com/scholar?q=Yibin+Yan+and+Weidi+Xie%2E+2024%2E+EchoSight%3A+Advancing+visual%2Dlanguage+models+with+wiki+knowledge%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2024%2C+pages+1538%E2%80%931551%2E)
31. Wei Yang, Jingjing Fu, Rui Wang, Jinyu Wang, Lei Song, and Jiang Bian. 2025. OMGM: Orchestrate multiple granularities and modalities for efficient multimodal retrieval. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 24545– 24… [find](https://scholar.google.com/scholar?q=Wei+Yang%2C+Jingjing+Fu%2C+Rui+Wang%2C+Jinyu+Wang%2C+Lei+Song%2C+and+Jiang+Bian%2E+2025%2E+OMGM%3A+Orchestrate+multiple+granularities+and+modalities+for+efficient+multimodal+retrieval%2E+In+Proceedings+of+the+63rd+Annu)
32. Peitian Zhang, Zheng Liu, Shitao Xiao, Zhicheng Dou, and Jian-Yun Nie. 2024a. A multi-task embedder for retrieval augmented LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3537–3553. [find](https://scholar.google.com/scholar?q=Peitian+Zhang%2C+Zheng+Liu%2C+Shitao+Xiao%2C+Zhicheng+Dou%2C+and+Jian%2DYun+Nie%2E+2024a%2E+A+multi%2Dtask+embedder+for+retrieval+augmented+LLMs%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Association+for+Compu)
33. Tao Zhang, Ziqi Zhang, Zongyang Ma, Yuxin Chen, Zhongang Qi, Chunfeng Yuan, Bing Li, Junfu Pu, Yuxuan Zhao, Zehua Xie, and 1 others. 2024b. mR 2 AG: Multimodal retrieval-reflection-augmented generation for knowledge-based VQA. arXiv preprint arXiv:2411.15041. — [arXiv:2411.15041](https://arxiv.org/abs/2411.15041) [find](https://scholar.google.com/scholar?q=Tao+Zhang%2C+Ziqi+Zhang%2C+Zongyang+Ma%2C+Yuxin+Chen%2C+Zhongang+Qi%2C+Chunfeng+Yuan%2C+Bing+Li%2C+Junfu+Pu%2C+Yuxuan+Zhao%2C+Zehua+Xie%2C+and+1+others%2E+2024b%2E+mR+2+AG%3A+Multimodal+retrieval%2Dreflection%2Daugmented+generatio)

*Updated 1 November 2026*