Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision
Open accessAbstract
Seongyun Lee, Sue Hyun Park, Yongrae Jo, Minjoon Seo. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Some approaches are validated only on small, specific constraint sets, limiting their general applicability.
“Some approaches are validated only on small, specific constraint sets, limiting their general applicability (Schick et al., 2023; Saunders et al., 2022; Lee et al., 2024; Mu et al., 2023; Yang et al., 2022; Gou et al., 2024; Varshney et al., 2023).”
From LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints (2024) · cites this paper as Lee et al., 2024
Section 4.1 (page unavailable) says VOLCANO was evaluated on five benchmarks spanning hallucination and general multimodal performance, including benchmarks with 9,000 and 4,377 questions. Appendix A (page unavailable) describes multiple task and question types. That is contrary to characterizing this approach as validated only on a small, specific constraint set; the paper’s Limitations section instead identifies execution time as its notable drawback. (LLM, conf=0.82)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 3
- Zhibin Gou, Zhihong Shao, Yeyun Gong, yelong shen, Yujiu Yang, Nan Duan, and Weizhu Chen. 2024. CRITIC: Large language models can self-correct with tool-interactive critiquing. In The Twelfth Inter- national Conference on Learning Representations.
- Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023b. Improved baselines with visual instruc- tion tuning. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023c. Visual instruction tuning. arXiv preprint arXiv:2304.08485. · arXiv
- Muru Zhang, Ofir Press, William Merrill, Alisa Liu, and Noah A. Smith. 2023a. How language model hallucinations can snowball.
Cited by
Sorted by citations
Kamoi, R., Zhang, Y., Zhang, N., Han, J., & Zhang, R. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00713 · Cited by 82 · see citing works
Large models for intelligent transportation systems and autonomous vehicles: A survey
Gan, L., Chu, W., Li, G., Tang, X., & Li, K. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102786 · Cited by 79 · see citing works
Wang, L., He, J., Li, S., Liu, N., & Lim, E. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-53302-0_3 · Cited by 31 · see citing works
Hallucinations of large multimodal models: Problem and countermeasures
Sun, S., Lin, Z., & Wu, X. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102970 · Cited by 25 · see citing works
A multimodal large language model for materials science
Tang, Y., Xu, W., Cao, J., Ma, J., Gao, W., Farrell, S., Erichson, N. B., Mahoney, M. W., Nonaka, A., & Yao, Z. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01214-y · Cited by 42 · see citing works
An, W., Tian, F., Leng, S., Nie, J., Lin, H., Wang, Q., Chen, P., Zhang, X., & Lu, S. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02784 · Cited by 32 · see citing works
Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs
Tu, C., Ye, P. D., Zhou, D., Bai, L., Yu, G., Chen, T., & Ouyang, W. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02607-z · Cited by 9 · see citing works
HaloQuest: A Visual Hallucination Dataset for Advancing Multimodal Reasoning
Wang, Z., Bingham, G., Yu, A. W., Le, Q. V., Luong, M.-T., & Ghiasi, G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72980-5_17 · Cited by 12 · see citing works
Wu, Y., Zhang, L., Yao, H., Du, J., Yan, K., Ding, S., Wu, Y., & Li, X. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01365 · Cited by 4 · see citing works
Wang, Y., Liu, Q., Fan, J., Hong, J., Chu, H., Tian, M., Gao, B., & Chen, H. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3673470 · Cited by 6 · see citing works
Huang, P.-H., Li, J.-L., Chen, C.-P., Chang, M.-C., & Chen, W.-C. (2024) · IEEE Workshop/Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00597 · Cited by 7 · see citing works
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of ExplainabilityPreprint
Shu, D., Zhao, H., Hu, J., Liu, W., Lu, C. Y., & Du, M. (2025) · Qeios · doi:10.32388/ooam1q · Cited by 4 · see citing works
Palmeira Ferraz, T., Mehta, K., Lin, Y.-H., Chang, H.-S., Oraby, S., Liu, S., Subramanian, V., Chung, T., Bansal, M., & Peng, N. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.458 · Cited by 3 · see citing works
Boosting Faithful Multi-Modal LLMs via Complementary Visual Grounding
Fu, Z., Mao, Z.-D., Zhang, L., & Zhang, Y.-D. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3644140 · Cited by 6 · see citing works
Fan, J.-Q., Wu, J.-H., Chu, H.-Q., Ge, Q.-B., & Gao, B.-Z. (2026) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2025.3625700 · Cited by 3 · see citing works
Li, Y., Wang, Y., Li, M., Li, X., & Feng, J. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.115962 · Cited by 1 · see citing works
Mitigating Multimodal Large Language Model Hallucinations Through Direct Preference Optimization
Yang, Y., & Zhang, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-2914-5_23
Liu, J., Zhang, T., He, B., Yuan, S., Chen, J., Lin, X., & Yu, X. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00550-8
Mitigating Hallucinations in Vision-Language Models via Contextual Entropy Calibration
Yin, X., Peng, D., & Wei, W. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810847
ESC: Emotional Self-correction for Reliable Vision Language Models
Nguyen, T.-H., Nguyen, M.-N., Huy, N. N., Nguyen, H. S., Nhat, H. N. M., Nguyen, T.-H., NGUYEN, C. T., Le, H. M., Nguyen, D. Q., Huynh, P. K., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37016-7_26
Seeing Red, Thinking Bad: Color Bias in Vision Language Models
Ide, K., Yamada, R., Fukuhara, Y., Kataoka, H., & Satoh, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31583-0_18
- Authors
- Lee, S., Park, S. H., Jo, Y., & Seo, M.
- Affiliations
- Korea Advanced Institute of Science and Technology (KR)
- LG AI Research (South Korea) (KR)
- ORCID
- Jo, Yongrae
- Venue
- Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
- Published
- 2024
- Pages
- 391-404
- OpenAlex
- W4401043235
- Cited by
- 20
- References
- 0
- Citations by year
- 2026: 7 · 2025: 9 · 2024: 4
- FWCI
- 4.14
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion, cc-by)
- Funders
- Korea Advanced Institute of Science and Technology (2019-0-00075)
- Ministry of Science and ICT, South Korea (2019-0-00075, No.2019-0-00075, 2022-0-00264)
- Institute for Information and Communications Technology Promotion (2022-, 2019-0-00075)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- multimodal hallucination, hallucination mitigation, self-feedback, revision, large language models, multimodal models
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
