A Review of Multi-Label and Multi-Document Research in Community Question Answering

Main Article Content

Yahan Tan
School of Software and Internet of Things Engineering, Jiangxi University of Finance and Economics, Nanchang 330013, Jiangxi, China

DOI: https://doi.org/10.70267/cai.v3n5.6376

Keywords

community question answering, multi-label text classification, multi-document question answering, large language models, retrieval-augmented generation, knowledge grounding

Abstract

Community Question Answering (CQA) platforms function as continuously evolving repositories of user-generated knowledge, where questions are often informal, intents may be multiple, evidence is distributed across sources, and knowledge changes over time. These characteristics limit the applicability of conventional single-label and single-document approaches to complex information needs. This review traces the evolution of CQA from retrieval and ranking through neural semantic matching and pretrained Transformer models to retrieval-augmented generation and large language models, with particular emphasis on multi-label question understanding and multi-document evidence integration. Existing studies are compared from the perspectives of semantic representation, intent modeling, evidence retrieval and fusion, knowledge grounding, and answer reliability. The literature shows that substantial progress has been made in individual capabilities, but a unified mechanism that coordinates multi-label intent interpretation, dynamic retrieval, evidence verification, and grounded generation remains insufficiently developed. Future research should therefore move toward closed-loop architectures and evaluation frameworks that jointly measure label identification, evidence coverage, source attribution, and final answer quality in realistic community settings.

Abstract 43 | PDF Downloads 8

References

  • [1]I. Srba and M. Bielikova, “A Comprehensive Survey and Classification of Approaches for Community Question Answering,” ACM Transactions on the Web, vol. 10, no. 3, Art. 18, pp. 1–63, 2016, doi:10.1145/2934687.
  • [2]J. Jeon, W. B. Croft, and J. H. Lee, “Finding similar questions in large question and answer archives,” in Proc. 14th ACM CIKM, 2005, pp. 84–90, doi:10.1145/1099554.1099572.
  • [3]M. Surdeanu, M. Ciaramita, and H. Zaragoza, “Learning to Rank Answers on Large Online QA Collections,” in Proc. ACL-08: HLT, 2008, pp. 719–727.
  • [4]P. Nakov, L. Màrquez, W. Magdy, A. Moschitti, J. Glass, and B. Randeree, “SemEval-2015 Task 3: Answer Selection in Community Question Answering,” in Proc. SemEval 2015, 2015, pp. 269–281, doi:10.18653/v1/S15-2047.
  • [5]A. Severyn and A. Moschitti, “Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks,” in Proc. 38th ACM SIGIR, 2015, pp. 373–382, doi:10.1145/2766462.2767738.
  • [6]M. Tan, C. dos Santos, B. Xiang, and B. Zhou, “Improved Representation Learning for Question Answer Matching,” in Proc. ACL, 2016, pp. 464–473, doi:10.18653/v1/P16-1044.
  • [7]X. Zhang, S. Li, L. Sha, and H. Wang, “Attentive Interactive Neural Networks for Answer Selection in Community Question Answering,” in Proc. AAAI, 2017, pp. 3525–3531, doi:10.1609/AAAI.V31I1.11006.
  • [8]J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186, doi:10.18653/v1/N19-1423.
  • [9]N. Reimers and I. Gurevych, “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks,” in Proc. EMNLP-IJCNLP, 2019, pp. 3982–3992, doi:10.18653/v1/D19-1410.
  • [10]Z. Ji et al., “Survey of Hallucination in Natural Language Generation,” ACM Computing Surveys, vol. 55, no. 12, Art. 248, 2023, doi:10.1145/3571730.
  • [11]P. Manakul, A. Liusie, and M. Gales, “SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models,” in Proc. EMNLP, 2023, pp. 9004–9017, doi:10.18653/v1/2023.emnlp-main.557.
  • [12]P. Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” in Advances in Neural Information Processing Systems 33, 2020.
  • [13]A. Vaswani et al., “Attention Is All You Need,” in Advances in Neural Information Processing Systems 30, 2017.
  • [14]T. Brown et al., “Language Models are Few-Shot Learners,” in Advances in Neural Information Processing Systems 33, 2020.
  • [15]S. Borgeaud et al., “Improving Language Models by Retrieving from Trillions of Tokens,” in Proc. 39th ICML, PMLR 162, 2022, pp. 2206–2240.
  • [16]Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun, M. Wang, and H. Wang, “Retrieval-Augmented Generation for Large Language Models: A Survey,” arXiv:2312.10997, 2023.
  • [17]K. Guu, K. Lee, Z. Tung, P. Pasupat, and M.-W. Chang, “REALM: Retrieval-Augmented Language Model Pre-Training,” in Proc. ICML, 2020, pp. 3929–3938.
  • [18]W. Yu, D. Iter, S. Wang, Y. Xu, M. Ju, S. Sanyal, C. Zhu, M. Zeng, and M. Jiang, “Generate Rather Than Retrieve: Large Language Models are Strong Context Generators,” in Proc. ICLR, 2023.
  • [19]S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K. Narasimhan, and Y. Cao, “ReAct: Synergizing Reasoning and Acting in Language Models,” in Proc. ICLR, 2023.
  • [20]N. Shinn, F. Cassano, A. Gopinath, K. Narasimhan, and S. Yao, “Reflexion: Language Agents with Verbal Reinforcement Learning,” in Advances in Neural Information Processing Systems 36, 2023.
  • [21]V. Liévin, C. E. Hother, A. G. Motzfeldt, and O. Winther, “Can Large Language Models Reason about Medical Questions?” Patterns, vol. 5, no. 3, Art. 100943, 2024, doi:10.1016/j.patter.2024.100943.
  • [22]K. Singhal et al., “Large Language Models Encode Clinical Knowledge,” Nature, vol. 620, pp. 172–180, 2023, doi:10.1038/s41586-023-06291-2.
  • [23]X. Hu, “Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models,” arXiv:2311.17502, 2023.
  • [24]G. Tsoumakas and I. Katakis, “Multi-Label Classification: An Overview,” International Journal of Data Warehousing and Mining, vol. 3, no. 3, pp. 1–13, 2007, doi:10.4018/jdwm.2007070101.
  • [25]M.-L. Zhang and Z.-H. Zhou, “A Review on Multi-Label Learning Algorithms,” IEEE Transactions on Knowledge and Data Engineering, vol. 26, no. 8, pp. 1819–1837, 2014, doi:10.1109/TKDE.2013.39.
  • [26]J. Liu, W.-C. Chang, Y. Wu, and Y. Yang, “Deep Learning for Extreme Multi-label Text Classification,” in Proc. 40th ACM SIGIR, 2017, pp. 115–124, doi:10.1145/3077136.3080834.
  • [27]P. Yang, X. Sun, W. Li, S. Ma, W. Wu, and H. Wang, “SGM: Sequence Generation Model for Multi-label Classification,” in Proc. COLING, 2018, pp. 3915–3926.
  • [28]R. You, Z. Zhang, Z. Wang, S. Dai, H. Mamitsuka, and S. Zhu, “AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification,” in Advances in Neural Information Processing Systems 32, 2019.
  • [29]L. Xiao, B.-L. Chen, X. Huang, H.-F. Liu, L.-P. Jing, and J. Yu, “Multi-label Text Classification Method Based on Label Semantic Information,” Journal of Software, vol. 31, no. 4, pp. 1079–1089, 2020, doi:10.13328/j.cnki.jos.005923.
  • [30]B. Li, J. Zhou, X. Jing, and N. Li, “Research on Automatic Multi-Label Text Classification for ICD-9-CM3,” Chinese Journal of Medicine, vol. 22, no. 17, pp. 51–56, 2025 [in Chinese].
  • [31]X. Li, J. Jiang, R. Dharmani, J. Srinivasa, G. Liu, and J. Shang, “Open-world Multi-label Text Classification with Extremely Weak Supervision,” in Proc. EMNLP, 2024, pp. 15084–15096, doi:10.18653/v1/2024.emnlp-main.841.
  • [32]D. Chen, A. Fisch, J. Weston, and A. Bordes, “Reading Wikipedia to Answer Open-Domain Questions,” in Proc. ACL, 2017, pp. 1870–1879, doi:10.18653/v1/P17-1171.
  • [33]Z. Yang, P. Qi, S. Zhang, Y. Bengio, W. Cohen, R. Salakhutdinov, and C. Manning, “HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering,” in Proc. EMNLP, 2018, pp. 2369–2380, doi:10.18653/v1/D18-1259.
  • [34]V. Karpukhin, B. Oguz, S. Min, P. Lewis, L. Wu, S. Edunov, D. Chen, and W.-t. Yih, “Dense Passage Retrieval for Open-Domain Question Answering,” in Proc. EMNLP, 2020, pp. 6769–6781, doi:10.18653/v1/2020.emnlp-main.550.
  • [35]A. Ni, M. Gardner, and P. Dasigi, “Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization,” in Proc. EMNLP, 2021, pp. 6149–6161, doi:10.18653/v1/2021.emnlp-main.497.
  • [36]A. Asai, Z. Wu, Y. Wang, A. Sil, and H. Hajishirzi, “Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection,” in Proc. ICLR, 2024.
  • [37]S.-Q. Yan, J.-C. Gu, Y. Zhu, and Z.-H. Ling, “Corrective Retrieval Augmented Generation,” arXiv preprint arXiv:2401.15884, 2024.
  • [38]Y. Li and M. Li, “Supplementary Q&A Recommendation Based on Transfer Learning Enhanced Multi-Label Multi-Document Classifier,” Data Analysis and Knowledge Discovery, vol. 8, no. 10, pp. 89–99, 2024, doi:10.11925/infotech.2096-3467.2023.0683.
  • [39]Z. Li, B. Zou, Y. Fan, and Y. Hong, “KEPR: Knowledge Enhancement and Plausibility Ranking for Generative Commonsense Question Answering,” in Proc. IEEE IJCNN, 2023, pp. 5163–5170.
  • [40]P. Bajaj et al., “MS MARCO: A Human Generated MAchine Reading COmprehension Dataset,” arXiv:1611.09268, 2016.
  • [41]T. Kwiatkowski et al., “Natural Questions: A Benchmark for Question Answering Research,” Transactions of the Association for Computational Linguistics, vol. 7, pp. 452–466, 2019, doi:10.1162/tacl_a_00276.
  • [42]P. Nakov, L. Màrquez, A. Moschitti, W. Magdy, H. Mubarak, A. A. Freihat, J. Glass, and B. Randeree, “SemEval-2016 Task 3: Community Question Answering,” in Proc. SemEval-2016, 2016, pp. 525–545, doi:10.18653/v1/S16-1083.
  • [43]P. Nakov et al., “SemEval-2017 Task 3: Community Question Answering,” in Proc. SemEval-2017, 2017, pp. 27–48, doi:10.18653/v1/S17-2003.
  • [44]B. Wen, J. Yao, S. Feng, C. Xu, Y. Tsvetkov, B. Howe, and L. L. Wang, “Know Your Limits: A Survey of Abstention in Large Language Models,” Transactions of the Association for Computational Linguistics, vol. 13, pp. 529–556, 2025, doi:10.1162/tacl_a_00754.
  • [45]Y. Li et al., “A Survey of RAG-Reasoning Systems in Large Language Models,” in Findings of EMNLP, 2025, pp. 12120–12145, doi:10.18653/v1/2025.findings-emnlp.648.

Article Sidebar

Full Text
PDF
Information
Copy Publication Information
Published
Oct 29, 2026
Issue
Vol. 3 No. 5 (2026)
Section
Research Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Tan, Y. (2026). A Review of Multi-Label and Multi-Document Research in Community Question Answering. Computers and Artificial Intelligence, 3(5), 63-76. https://doi.org/10.70267/cai.v3n5.6376