Automated Molecular Concept Generation and Labeling with Large Language Models: Human Oversight and Decision Accountability

Human oversight is meaningful when intervention points, responsibility, escalation paths, and the evidence available to decision makers are explicitly defined. This structured evidence review evaluates "Automated Molecular Concept Generation and Labeling with Large Language Models" alongside nine author-disjoint, topically matched publications in language-centered multimodal learning. It compares construct definitions, evaluation choices, operating assumptions, and reported limitations instead of treating bibliographic similarity as empirical equivalence. Viewed through human oversight and decision accountability, the map separates claims supported by the available record from questions that still require full-text extraction, replication, or new experiments. The synthesis is interpretive rather than meta-analytic and therefore does not present a pooled effect estimate or a new causal result. The resulting agenda specifies reviewer authority, override logging, escalation procedures, and evaluation of automation bias.

1. Zhang, Z., Wu, Q., Xia, B., Sun, F., Hu, Z., Sun, Y., & Zhang, S. (2025). Automated Molecular Concept Generation and Labeling with Large Language Models. In Proceedings of the 31st International Conference on Computational Linguistics (pp. 6918–6936).
2. Fan, Y., & Strube, M. (2025). Consistent Discourse-level Temporal Relation Extraction Using Large Language Models. Findings of the Association for Computational Linguistics: EMNLP 2025, 18605-18622. https://doi.org/10.18653/v1/2025.findings-emnlp.1010 DOI
3. He, W., Ma, H., Li, S., Dong, H., Zhang, H., & Feng, J. (2023). Using Augmented Small Multimodal Models to Guide Large Language Models for Multimodal Relation Extraction. Applied Sciences, 13(22), 12208. https://doi.org/10.3390/app132212208 DOI
4. HE, L., WANG, R., DUAN, J., WANG, H., & LI, X. (2026). LLM-VGA: Large Language Model-Augmented Visual Generation with Hierarchical Bidirectional Alignment for Multimodal Relation Extraction. IEICE Transactions on Information and Systems. https://doi.org/10.1587/transinf.2025edp7173 DOI
5. Li, Z., Pang, N., & Zhao, X. (2024). Instruction Tuning Large Language Models for Multimodal Relation Extraction Using LoRA. Lecture Notes in Computer Science, 364-376. https://doi.org/10.1007/978-981-97-7707-5_30 DOI
6. Aidynkyzy, A. (2026). FROM NAMED ENTITY RECOGNITION TO RELATION EXTRACTION: LARGE LANGUAGE MODEL ASSISTED CONSTRUCTION OF THE KAZAKH RELATION EXTRACTION DATASET. Вестник Академии гражданской авиации, 41(2). https://doi.org/10.53364/24138614_2026_41_2_13 DOI
7. Liu, B., & Qi, G. (2025). LLM-CG: Large language model-enhanced constraint graph for distantly supervised relation extraction. Neurocomputing, 655, 131426. https://doi.org/10.1016/j.neucom.2025.131426 DOI
8. Zhao, H., Yilahun, H., & Hamdulla, A. (2023). Pipeline Chain-of-Thought: A Prompt Method for Large Language Model Relation Extraction. 2023 International Conference on Asian Language Processing (IALP), 31-36. https://doi.org/10.1109/ialp61005.2023.10337264 DOI
9. Choi, G., & Kim, H. (2025). Automated Claim–Evidence Extraction for Political Discourse Analysis: A Large Language Model Approach to Rodong Sinmun Editorials. Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER), 1-17. https://doi.org/10.18653/v1/2025.fever-1.1 DOI
10. Shah, P. (2025). Multimodal Large Language Model (MLLM) Noise Resistance. . https://doi.org/10.33774/coe-2025-6z9zx DOI