Enhancing Multi-modal Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation
The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
Multi-modal multi-hop question answering involves answering a question by reasoning over multiple input sources from different modalities. Existing methods often retrieve evidences separately and then use a language model to generate an answer based on the retrieved evidences, and thus do not adequately connect candidates and are unable to model the interdependent relations during retrieval. Moreover, the pipelined approaches of retrieval and generation might result in poor generation performance when retrieval performance is low. To address these issues, we propose a Structured Knowledge and Unified Retrieval-Generation (SKURG) approach. SKURG employs an Entity-centered Fusion Encoder to align sources from different modalities using shared entities. It then uses a unified Retrieval-Generation Decoder to integrate intermediate retrieval results for answer generation and also adaptively determine the number of retrieval steps. Extensive experiments on two representative multi-modal multi-hop QA datasets MultimodalQA and WebQA demonstrate that SKURG outperforms the state-of-the-art models in both source retrieval and answer generation performance with fewer parameters1.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“It uses a gate score to determine whether to re-start retrieval or to generate the real answer.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [277]
In the citing paper
“SKURG [277] performs iterative retrieval and generation, using cross-attention to incorporate data sources into the input embedding.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [277]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Know What You Don't Know: Unanswerable Questions for SQuAD
Rajpurkar, P., Jia, R., & Liang, P. (2018) · arXiv · doi:10.48550/arxiv.1806.03822 · Cited by 2,242
Know What You Don’t Know: Unanswerable Questions for SQuAD
Rajpurkar, P., Jia, R., & Liang, P. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p18-2124 · Cited by 2,240
BARTScore: Evaluating Generated Text as Text Generation
Yuan, W., Neubig, G., & Liu, P. (2021) · arXiv · doi:10.48550/arxiv.2106.11520 · Cited by 353
♫ MuSiQue: Multihop Questions via Single-hop Question Composition
Trivedi, H., Balasubramanian, N., Khot, T., & Sabharwal, A. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00475 · Cited by 283
Research works printed but not linked: 31
- Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, and Caiming Xiong. 2019. Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering. In International Conference on Learning Representations.
- 10.1109/CVPR52688.2022.01600 · DOI
- Wenhu Chen, Hexiang Hu, Xi Chen, Pat Verga, and William Cohen. 2022. MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text. (Dec. 2022), 5558--5570.
- Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations.
- Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, and Matt Gardner. 2019. DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, 2368--2378.
- 10.18653/v1/D19-3029 · DOI · Paper page
- 10.18653/v1/2022.findings-emnlp.303 · DOI
- 10.18653/v1/P17-2049 · DOI · Paper page
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.).
- 10.1007/978-3-030-58577-8_8 · DOI · Paper page
- 10.18653/v1/2022.acl-long.290 · DOI
- Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019). · arXiv
- Zhenghao Liu, Chenyan Xiong, Yuanhuiyi Lv, Zhiyuan Liu, and Ge Yu. 2022. Universal Multi-Modality Retrieval with One Unified Embedding Space. CoRR, Vol. abs/2209.00179 (2022). showeprint[arXiv]2209.00179 · arXiv
- 10.1109/CVPR42600.2020.01045 · DOI · Paper page
- 10.1145/3331184.3331252 · DOI · Paper page
- 10.18653/v1/2022.acl-long.395 · DOI · Paper page
- 10.1609/aaai.v34i05.6364 · DOI · Paper page
- Sewon Min, Danqi Chen, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2019. Knowledge guided text retrieval and reading for open domain question answering. arXiv preprint arXiv:1911.03868 (2019). · arXiv
- 10.18653/v1/2022.findings-naacl.115 · DOI · Paper page
- 10.18653/v1/P17-1161 · DOI · Paper page
- 10.18653/v1/2021.emnlp-main.292 · DOI · Paper page
- 10.1609/aaai.v36i10.21370 · DOI
- 10.18653/v1/P16-1162 · DOI · Paper page
- Alon Talmor, Ori Yoran, Amnon Catav, Dan Lahav, Yizhong Wang, Akari Asai, Gabriel Ilharco, Hannaneh Hajishirzi, and Jonathan Berant. 2020. MultiModalQA: complex question answering over text, tables and images. In International Conference on Learning Representations.
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017).
- 10.1145/2629489 · DOI · Paper page
- 10.18653/v1/2022.emnlp-main.39 · DOI · Paper page
- 10.18653/v1/2022.acl-long.69 · DOI
- 10.18653/v1/2022.acl-long.416 · DOI · Paper page
- 10.18653/v1/2022.acl-long.340 · DOI · Paper page
- 10.1109/CVPR46437.2021.00553 · DOI · Paper page
Cited by
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024) · arXiv · doi:10.48550/arxiv.2402.19473 · Cited by 240
“SKURG [309] forms a knowledge graph using text and image data, then updates each source’s representation with their relevant sources.”
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation
Abootorabi, M. M., Zobeiri, A., Dehghani, M., Mohammadkhani, M., Mohammadi, B., Ghahroodi, O., Baghshah, M. S., & Asgari, E. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.861 · Cited by 76
Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs
Wang, Z., Li, Z., Jiang, Z., Tu, D., & Shi, W. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.281 · Cited by 12
Metadata
- Authors
- Yang, Q., Chen, Q., Wang, W., Hu, B., & Zhang, M.
- Affiliations
- Harbin Institute of Technology, Shenzhen, China
- Unaffiliated, Hangzhou, China
- Venue
- Proceedings of the 31st ACM International Conference on Multimedia
- Publisher
- ACM
- Published
- 2023-10-26
- Pages
- 5223-5234
- Cited by
- 12
- References
- 8
- Funders
- Strategic Emerging Industry Development Special Funds of Shenzhen (JCYJ20200109113403826)
- Natural Science Foundation of China (62006061)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Enhancing Multi-modal Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation. https://app.cochat.ai/papers/10.1145/3581783.3611964
- The paper
- Yang, Q., Chen, Q., Wang, W., Hu, B., & Zhang, M. (2023). Enhancing Multi-modal Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation. Proceedings of the 31st ACM International Conference on Multimedia. https://doi.org/10.1145/3581783.3611964
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.