DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs
The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
LLMs acquire knowledge from massive data snapshots collected at different timestamps.Their knowledge is then commonly evaluated using static benchmarks.However, factual knowledge is generally subject to timesensitive changes, and static benchmarks cannot address those cases.We present an approach to dynamically evaluate the knowledge in LLMs and their time-sensitiveness against Wikidata, a publicly available up-to-date knowledge graph.We evaluate the time-sensitive knowledge in twenty-four private and opensource LLMs, as well as the effectiveness of four editing methods in updating the outdated facts.Our results show that 1) outdatedness is a critical problem across state-of-the-art LLMs; 2) LLMs output inconsistent answers when prompted with slight variations of the question prompt; and 3) the performance of the stateof-the-art knowledge editing algorithms is very limited, as they can not reduce the cases of outdatedness and output inconsistency.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
In the citing paper
“However, current large language models (LLMs) like GPT-4 struggle with professional MCQG due to outdated knowledge, hallucination issues, and prompt sensitivity, resulting in unsatisfactory quality and difficulty.”
From MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback (2025) · cites this paper as Mousavi et al., 2024
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
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441 · cited 1×
“5) 3 , Bloom (7B) (Workshop et al., 2022), Flan-T5 XL (Chung et al., 2022), GPT-4 4 , Llama-2 (7B) & Llama-2 Chat (7B) (Touvron et al., 2023), Falcon (7B) & Falcon Instruct (7B) (Almazrouei et al., 2023), Vicuna v1.”
Transformer Feed-Forward Layers Are Key-Value Memories
Geva, M., Schuster, R., Berant, J., & Levy, O. (2020) · arXiv · doi:10.48550/arxiv.2012.14913 · Cited by 353
Transformer Feed-Forward Layers Are Key-Value Memories
Geva, M., Schuster, R., Berant, J., & Levy, O. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.446 · Cited by 353
Jiang, A. Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D. S., Casas, D. D. L., Bressand, F., Lengyel, G., Lample, G., Saulnier, L., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.06825 · Cited by 340
Evaluating the Ripple Effects of Knowledge Editing in Language Models
Cohen, R., Biran, E., Yoran, O., Globerson, A., & Geva, M. (2024) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00644 · Cited by 134
(2023) · doi:10.18653/v1/2023.emnlp-main.632 · Cited by 115
Editing Large Language Models: Problems, Methods, and Opportunities
Yao, Y., Wang, P., Tian, B., Cheng, S., Li, Z., Deng, S., Chen, H., & Zhang, N. (2023) · arXiv · doi:10.48550/arxiv.2305.13172 · Cited by 115
Mitchell, E., Lin, C., Bosselut, A., Finn, C., & Manning, C. D. (2021) · arXiv · doi:10.48550/arxiv.2110.11309 · Cited by 95
OLMo: Accelerating the Science of Language Models
Groeneveld, D., Beltagy, I., Walsh, E., Bhagia, A., Kinney, R., Tafjord, O., Jha, A., Ivison, H., Magnusson, I., Wang, Y., et al. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.841 · Cited by 70
Dolma: an open corpus of three trillion tokens for language model pretraining research
Soldaini, L., Kinney, R., Bhagia, A., Schwenk, D., Atkinson, D., Authur, R., Bogin, B., Chandu, K., Dumas, J., Elazar, Y., et al. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.840 · Cited by 56
Cited by
Yao, Z., Parashar, A., Zhou, H., Jang, W. S., Ouyang, F., Yang, Z., & Yu, H. (2025) · Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) · doi:10.18653/v1/2025.naacl-long.538 · Cited by 27
Madrid-García, A., Benavent, D., & Merino-Barbancho, B. (2025) · EULAR Rheumatology Open · doi:10.1016/j.ero.2025.06.012 · Cited by 9
“Key limitations include a propensity for medical hallucinations [11], reliance on potentially outdated knowledge [12] and an inability to dynamically access real-time data or interact directly with external tools like databases or electronic health records (EHRs).”
Metadata
- Authors
- Mousavi, S. M., Alghisi, S., & Riccardi, G.
- Venue
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Published
- 2024
- Pages
- 8014-8029
- Cited by
- 11
- References
- 17
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs. https://app.cochat.ai/papers/10.18653/v1/2024.findings-emnlp.471
- The paper
- Mousavi, S. M., Alghisi, S., & Riccardi, G. (2024). DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs. Findings of the Association for Computational Linguistics: EMNLP 2024. https://doi.org/10.18653/v1/2024.findings-emnlp.471
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.