The DOI matches its Crossref record, with a small difference in title or year; 1 of the 1 references it cites were found in a registry or an index.
Towards Verifiable Text Generation with Evolving Memory and Self-Reflection
Open accessAbstract
Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination.A promising solution to this issue is verifiable text generation, which prompts LLMs to generate content with citations for accuracy verification.However, verifiable text generation is non-trivial due to the focus-shifting phenomenon, the intricate reasoning needed to align the claim with correct citations, and the dilemma between the precision and breadth of retrieved documents.In this paper, we present VTG, an innovative framework for Verifiable Text Generation with evolving memory and self-reflection.VTG introduces evolving long short-term memory to retain both valuable documents and recent documents.A two-tier verifier equipped with an evidence finder is proposed to rethink and reflect on the relationship between the claim and citations.Furthermore, active retrieval and diverse query generation are utilized to enhance both the precision and breadth of the retrieved documents.We conduct extensive experiments on five datasets across three knowledge-intensive tasks and the results reveal that VTG significantly outperforms baselines.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
Existing long-term memory methods typically follow two directions: continuously recording, summarizing, and updating dialogue histories as memory, or transforming conversations into structured graph-based memory using OpenIE.
“These approaches typically follow two directions: (i) continuously recording, summarizing, and updating dialogue histories as memory [2, 23, 39, 44], or (ii) transforming conversations into structured graphbased memory using techniques such as OpenIE [19, 40, 57, 58].”
From HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues (2026) · cites this paper as [39]
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
Sorted by citations
From Matching to Generation: A Survey on Generative Information Retrieval
Li, X., Jin, J., Zhou, Y., Zhang, Y., Zhang, P., Zhu, Y., & Dou, Z. (2025) · ACM Transactions on Information Systems · doi:10.1145/3722552 · Cited by 172
Self-citationTool learning with large language models: a survey
Qu, C., Dai, S., Wei, X., Cai, H., Wang, S., Yin, D., Xu, J., & Wen, J.-R. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-024-40678-2 · Cited by 261
Self-citationShapefileGPT: a multi-agent large language model framework for automated shapefile processing
Lin, Q., Hu, R., Li, H., Wu, S., Li, Y., Fang, K., Feng, H., Du, Z., & Xu, L. (2025) · International Journal of Digital Earth · doi:10.1080/17538947.2025.2577884 · Cited by 34
Training Language Models to Generate Text with Citations via Fine-grained Rewards
Huang, C., Wu, Z., Hu, Y., & Wang, W. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.161 · Cited by 35
Xia, S., Wang, X., Liang, J., Zhang, Y., Zhou, W., Deng, J., Yu, F., & Xiao, Y. (2025) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2025.findings-naacl.55 · Cited by 28
Self-citationLyu, Y., Niu, Z., Xie, Z., Zhang, C., Xu, T., Wang, Y., & Chen, E. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.270 · Cited by 18
PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
Wu, J., Cai, H., Yan, L., Sun, H., Li, X. D., Wang, S., Yin, D., & Gao, M. J. (2025) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2025.naacl-long.459 · Cited by 7
Self-citationLM2: A Simple Society of Language Models Solves Complex Reasoning
Juneja, G., Dutta, S., & Chakraborty, T. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.920 · Cited by 7
Towards Verifiable Text Generation with Generative Agent
Ji, B., Liu, H., Du, M., Li, S., Liu, X., Ma, J., Yu, J., & Ng, S.-K. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i23.34599 · Cited by 4
Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey
Zhao, Y., Liu, Z., Zheng, Y., & Lam, K. (2026) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic68212.2026.11454197 · Cited by 4
On the Capacity of Citation Generation by Large Language Models
Qian, H., Fan, Y., Zhang, R., & Guo, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-1710-4_9 · Cited by 6
AWeCita: Generating Answer with Appropriate and Well-grained Citations Using LLMs
Zhao, S., Zhou, T., Jin, Z., Yuan, H., Chen, Y., Liu, K., & Li, S. (2024) · Data Intelligence · doi:10.3724/2096-7004.di.2024.0035 · Cited by 2
CiteLab: Developing and Diagnosing LLM Citation Generation Workflows via the Human-LLM Interaction
Shen, J., Zhou, T., Chen, Y., Liu, K., & Zhao, J. H. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-demo.47 · Cited by 2
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
Zhong, Y., Gao, Y., & Wang, H. (2026) · Proceedings of the ACM Web Conference 2026 · doi:10.1145/3774904.3792089 · Cited by 1
C 2 -Cite: Contextual-Aware Citation Generation for Attributed Large Language Models
Yu, Y., Bai, T., Lan, H., Qian, L., Peng, L., Wu, J., Liu, W., Luan, J., & Shi, C. (2026) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3773966.3777933 · Cited by 2
MAVIS: A Benchmark for Multimodal Source Attribution in Long-form Visual Question Answering
Song, S.-H., Park, M., & Kim, G. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i39.40585 · Cited by 1
Gao, S., Wang, G., & Li, X. (2025) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai65422.2025.11189588
Li, Z., Li, X., Mao, Y., Cao, L., Huang, W., Ren, J., & Yang, W. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461824
Multi-agent autonomous GeoAI framework for scalable and self-improving geospatial intelligence
Nguyen, K.-S., Nguyen, T.-V., Nguyen, V.-V., Luong, T. M.-H., Nguyen, H.-K., & Nguyen, D.-B. (2026) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v15.i3.pp2201-2215
A Framework of Reflective Agents with Adaptive Collaboration for Attributed Summary Generation
Chen, Y., Chen, P., Zheng, Z., & Wang, B. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.1366
Self-citationLi, Q., Wang, Z., Liu, Y., Ge, X., & Wang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-7738-4_23
Self-citation
Metadata
- Authors
- Sun, H., Cai, H., Wang, B., Hou, Y., Wei, X., Wang, S., Zhang, Y., & Yin, D.
- Affiliations
- Peking University (CN)
- Chinese Academy of Sciences (CN)
- Beijing Institute of Technology (CN)
- Baidu (China) (CN)
- Venue
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Published
- 2024
- Pages
- 8211-8227
- OpenAlex
- W4404783066
- Cited by
- 8
- References
- 0
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 1
- FWCI
- 2.31
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Keywords
- hallucination mitigation, large language models, long short-term memory, self-reflection, query generation
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
