The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Conflict-aware uncertainty alignment for tool-augmented document-centric multimodal intelligence
Overview
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
Verification
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.
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
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · cited 2×
“Ji et al. [25] categorize hallucinations into intrinsic hallucinations, which contradict source evidence, and extrinsic hallucinations, which introduce unsupported information beyond the available context.”
Understanding deep learning (still) requires rethinking generalization
Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2021) · Communications of the ACM · doi:10.1145/3446776 · Cited by 2,400
Gorilla: Large Language Model Connected with Massive APIs
Patil, S. G., Zhang, T., Wang, X., & Gonzalez, J. E. (2023) · arXiv · doi:10.48550/arxiv.2305.15334 · Cited by 226
API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
Li, M., Zhao, Y., Yu, B., Song, F., Li, H., Yu, H., Li, Z., Huang, F., & Li, Y. (2023) · arXiv · doi:10.48550/arxiv.2304.08244 · Cited by 124
Research works printed but not linked: 53
- Guo Z, Cheng S, Niu Y, Wang H, Zhou S, Huang W, et al. StableToolBench-MirrorAPI: modeling tool environments as mirrors of 7,000+ real-world APIs. In: Findings of ACL; 2025. p. 5247–5270. · DOI
- Xu H, Wang Z, Zhu Z, Pan L, Chen X, Fan S, et al. Alignment for efficient tool calling of large language models. In: EMNLP; 2025. p. 17787–17803. · DOI
- Wang H, Huang Y, Huang H, Wang Y, Li J, Gui G. Uncertainty-aware dynamic fusion network. Inf Fusion. 2025;123:103249. · DOI
- Zhang K, Xu W, Miao Z, Tian Y, Cen Y, Liu Y, et al. Causal learning with uncertainty-aware transformer. Neurocomputing. 2026;665:132196. · DOI
- Ye J, Li S, Li G, Huang C, Gao S, Wu Y, et al. Toolsword: safety issues of LLM tool learning. In: ACL; 2024. p. 2181–2211. · DOI
- Guan S, Wang J, Bian J, Zhu B, Lou JG, Xiong H. Evaluating LLM-based agents for multi-turn conversations: a survey. ACM Trans Intell Syst Technol. 2026;17(4):1–40. · DOI
- Carraro D, Bridge D. Recommendation diversity with LLMs. ACM Trans Recomm Syst. 2025;4(2):1–40. · DOI
- Spanos D, Passalis N, Tefas A. Improving uncertainty estimation in DNNs. Pattern Recognit. 2025;112267. · DOI
- Han Y, Liu Z, Yuan Z, Pu Y, Wang C, Song S, et al. Latency-aware unified networks. IEEE Trans Pattern Anal Mach Intell. 2024;46(12):7760–74. · DOI
- Hamdi A, Pontes EL, Sidere N, Coustaty M, Doucet A. Impact of OCR errors on NER. Nat Lang Eng. 2023;29(2):425–48. · DOI
- Hemmer A, Coustaty M, Bartolo N, Ogier JM. Confidence-aware document OCR error detection. In: Document analysis systems; Springer; 2024. p. 213–228. · DOI
- Catak FO, Kuzlu M. Uncertainty quantification in large language models through convex hull analysis. Discov Artif Intell. 2024;4:90. · DOI
- Wang P, Wu Q, Shen C, Dick A, Van Den Hengel A. FVQA. IEEE Trans Pattern Anal Mach Intell. 2017;40(10):2413–27. · DOI
- Wang Y, Lin Q, Shi J, An Y, Liu J, Wei B, et al. Explainable VQA survey. Inf Fusion. 2026;132:104215. · DOI
- Zhao Y, Tao Q, Sun P, Huang J, Song W, Hu N. HPRNet for image captioning. Pattern Recognit. 2026;177:113249. · DOI
- Khan MZ, Nguyen DT, Nguyen TT, et al. Cross-attention for VQA. Multimed Tools Appl. 2025;84(15):47543–65. · DOI
- Huang H, Qin Q. Cross-modal representation for retrieval. Multimed Syst. 2025;31(6):331. · DOI
- Naeem MF, Xian Y, Zhai X, Hoyer L, Van Gool L, Tombari F. SILC vision-language pretraining. In: ECCV; Springer; 2025.
- Ma X, Xie H, Qin SJ. Integrating LLMs with visual perception. Inf Fusion. 2026;125:103419. · DOI
- Ashqar HI, Jaber A, Alhadidi TI, Elhenawy M. Multimodal LLMs for transportation detection. Computation. 2025;13(6):133. · DOI
- Zhang Y, Wang M, Li X, Ren K, Zhu C, Naseem U. TurnBench-MS. In: Findings of EMNLP; 2025. p. 19892–19924. · DOI
- Prasad A, Koller A, Hartmann M, Clark P, Sabharwal A, Bansal M, et al. ADAPT planning with LLMs. In: NAACL; 2024. p. 4226–4252. · DOI
- Qu C, Dai S, Wei X, et al. Tool learning survey. Front Comput Sci. 2025;19:198343. · DOI
- Ye J, Li G, Gao S, Huang C, Wu Y, Li S, et al. ToolEyes evaluation. In: COLING; 2025. p. 156–187.
- Pandit T, Mahendru S, Raval M, Upadhyay D. Evolution of reranking models. In: ICCLNP; Springer; 2025. p. 56–67. · DOI
- He W, Jiang Z, Xiao T, Xu Z, Li Y. Uncertainty quantification survey. ACM Comput Surv. 2025.
- Fang G, Ma X, Mi MB, Wang X. Isomorphic pruning. In: ECCV; Springer; 2024. p. 232–250. · DOI
- Chen M, Wei G, Yuan S, et al. Plasmonic neural device. Sci China Mater. 2025;68:3703–14. · DOI
- Ramesh G, Sahil M, Palan SA. Zero-shot and few-shot NLP review. Discov Appl Sci. 2025;7:966. · DOI
- Muthusami R, Saritha K. Adaptive mixture-of-recursions vision transformer with joint depth routing for multimedia vision. Multimed Tools Appl. 2026;85:675. · DOI
- Huang J, Zhang J, Jiang K, et al. Visual instruction tuning survey. Int J Comput Vis. 2025;133:8151–89. · DOI
- Hamid OH. There is more to AI than meets the eye: aligning man-made algorithms with nature-inspired mechanisms. In: IEEE/ACS International Conference on Computer Systems and Applications; IEEE; 2022. p. 1–4. · DOI
- Hamid OH. Data-centric and model-centric AI: twin drivers of compact and robust Industry 4.0 solutions. Appl Sci. 2023;13(5):2753. · DOI
- Hamid OH. ChatGPT and the Chinese room argument: an eloquent AI conversationalist lacking true understanding and consciousness. In: IEEE international conference on information technology trends; IEEE; 2023. p. 238–241. · DOI
- Ma Z, Liu J, Luo X, Huang Z, Zhu Q, Che W. Meta-verification for tool-augmented LLMs. In: KDD; 2025. p. 2078–2089. · DOI
- Franchi G, Laurent O, Leguéry M, Bursuc A, Pilzer A, Yao A. Bayesian uncertainty estimation. In: CVPR; 2024. p. 12194–12204. · DOI
- Detommaso G, Gasparin A, Donini M, Seeger M, Wilson AG, Archambeau C. Fortuna UQ library. J Mach Learn Res. 2024;25:1–7.
- Huang S, Zhong W, Lu J, Zhu Q, Gao J, Liu W, et al. Benchmarking tool utilization. In: Findings of ACL; 2024. p. 4363–4400. · DOI
- Teney D, Nicolicioiu AM, Hartmann V, Abbasnejad E. Neural redshift. In: CVPR; 2024. p. 4786–4796. · DOI
- Li C, Xu H, Tian J, Wang W, Yan M, Bi B, et al. mPLUG vision-language learning. In: EMNLP; 2022. p. 7241–7259. · DOI
- Wang W, et al. InternVL. In: Large Vision-Language Models; Springer; 2026. · DOI
- Joshi K, Arolkar H. Tesseract OCR review for Indian languages. In: Cognitive computing and cyber physical systems; Springer; 2025.
- Ma W, Cao M, Ma J, Dong Z, Yang C, Li Z. Mamba-YOLO for document layout. Pattern Recognit. 2026;170:112031. · DOI
- Yang L, Yang Z, Li F, et al. Single-layer feedforward networks with dynamic width. Sci China Inf Sci. 2025;68:182205. · DOI
- Cai R, Huang S, Qiao J, et al. Online causal reinforcement learning framework. Sci China Inf Sci. 2026;69:122104. · DOI
- Su M, Yuan Q, Qu P, et al. Dual-arm cooperative control using PPO. J King Saud Univ Comput Inf Sci. 2026;38:45. · DOI
- Liu C, Li S, Xu M, Maimaiti M, Silamu W. Scene text recognition via dual decoder. In: PRCV; Springer; 2026.
- Mathew M, Karatzas D, Jawahar CV. DocVQA dataset. In: WACV; 2021. p. 2200–2209.
- Jaume G, Ekenel HK, Thiran JP. FUNSD dataset. arXiv. 2019. https://doi.org/10.48550/arXiv.1905.13538 · DOI
- Huang Z, Chen Y, Yu H. SROIE competition. In: ICDAR; IEEE; 2019. p. 1488–1493.
- Zhong X, Tang J, Yepes AJ. PubLayNet dataset. In: ICDAR; IEEE; 2019. p. 1015–1022. · DOI
- Chen S, Yuan J, Zhang Y, et al. Domain adversarial learning. Front Comput Sci. 2025;19:1912378. · DOI
- Wang Y, Deng Y, Zheng Y, Chattopadhyay P, Wang L. Vision transformer survey. Technologies. 2025;13(1):32. · DOI
Metadata
- Authors
- Muthusami, R., & Saritha, K.
- Venue
- Discover Artificial Intelligence
- Published
- 2026-10-05
- Volume
- 6
- Issue
- 1
- ISSN
- 2731-0809
- Cited by
- 0
- References
- 5
- Language
- en
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
