Elamur Research⌕
☰
home / papers / 2026 / When Facts Change: Temporal Knowledge Conflict Resolution in LLMs

When Facts Change: Temporal Knowledge Conflict Resolution in LLMs

Paper · 2026 · Jonas Wallat, Wolfgang Nejdl and Sandipan Sikdar

Summary

The paper examines how LLMs handle clashes between what they learned in training and what a prompt tells them. It focuses on clashes caused by time: facts that changed after the model's knowledge cutoff. The authors ask whether mutability, meaning how likely a fact is to change, helps models decide which source to trust.

To test this, they build WikiRecentChanges, a re-computable benchmark drawn from Wikidata. It pairs genuinely stable facts, such as birthplaces, with facts that changed in 2025, such as team memberships. Each fact gets either a true or a counterfactual context paragraph. They then study reasoning models' traces and answers, with and without prompts asking them to consider mutability.

Models often mention temporal change in their reasoning for updated facts and rarely do so for stable ones. Yet this distinction seldom shows up in their final answers. Prompting for mutability increases such mentions but does not raise accuracy. The weak point depends on scale: small models miss the conflict, while large models notice it but do not act on it. This matters for RAG systems, where retrieved text may be outdated or false.

Key points

  • New resource: WikiRecentChanges is derived from Wikidata and can be regenerated as time passes. It separates truly stable facts from facts updated in 2025. Code and data are at github.com/jwallat/knowledge-conflicts-mutability.
  • Why not EvoWiki: The authors argue the existing EvoWiki benchmark is unsuitable for two reasons. Its 2021 to mid-2024 window predates current model cutoffs. Its "stable" split also includes mutable facts that simply happened not to change.
  • Design: The study tests every combination of fact category (stable or updated) and supplied context (true or counterfactual). The analysis centres on two diagnostic cells: stable facts with counterfactual context, and updated facts with true context.
  • Reasoning vs. prediction gap: Verbalized mutability reasoning, whether spontaneous or prompted, does not reliably change final predictions. This points to a disconnect between reasoning traces and answers.
  • Susceptibility to misinformation: A single high-quality counterfactual paragraph misled models in most cases. The authors warn that steering methods which force reliance on context can make such errors worse.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Jonas Wallat, Wolfgang Nejdl and Sandipan Sikdar. 2026. When Facts Change: Temporal Knowledge Conflict Resolution in LLMs. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.103

@inproceedings{wallat2026when,
  title = {{When Facts Change: Temporal Knowledge Conflict Resolution in LLMs}},
  author = {Jonas Wallat, Wolfgang Nejdl and Sandipan Sikdar},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.103},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.103}
}

References

47 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Marah I Abdin, Sahaj Agarwal, Ahmed Awadallah, Vidhisha Balachandran, Harkirat S. Behl, Lingjiao Chen, Baolong Bi, Shenghua Liu, Yiwei Wang, Yilong Xu, Junfeng Fang, Lingrui Mei, and Xueqi Cheng. 2025. Parameters vs. context: Fine-grained control of knowledge reliance in language models. CoRR, abs/2… — [arXiv:2503.15888](https://arxiv.org/abs/2503.15888) find
  2. Jannis Bulian, Christian Buck, Wojciech Gajewski, Benjamin Börschinger, and Tal Schuster. 2022. Tomayto, tomahto. beyond token-level answer equivalence for question answering evaluation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi,…
  3. Hung-Ting Chen, Michael J. Q. Zhang, and Eunsol Choi. 2022. Rich knowledge sources bring complex knowledge conflicts: Recalibrating models to reflect conflicting evidence. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Em…
  4. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chengg… — DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  5. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, Aurélien Rodriguez,… — The Llama 3 Herd of Models
  6. Tianqing Fang, Zhaowei Wang, Wenxuan Zhou, Hongming Zhang, Yangqiu Song, and Muhao Chen. 2024. Getting sick after seeing a doctor? diagnosing and mitigating knowledge conflicts in event temporal reasoning. In Findings of the Association for Computational Linguistics: NAACL 2024, Mexico City, Mexico,… find
  7. Mehrdad Farahani and Richard Johansson. 2024. Deciphering the interplay of parametric and non-parametric memory in retrieval-augmented language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Miami, FL, USA, November 12-16, 2024, pages 1… find
  8. Constanza Fierro, Nicolas Garneau, Emanuele Bugliarello, Yova Kementchedjhieva, and Anders Søgaard. 2024. Mulan: A study of fact mutability in language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technol… find
  9. Yufang Hou, Alessandra Pascale, Javier Carnerero-Cano, Tigran T. Tchrakian, Radu Marinescu, Elizabeth Daly, Inkit Padhi, and Prasanna Sattigeri. 2024. Wikicontradict: A benchmark for evaluating llms on real-world knowledge conflicts from wikipedia. In Advances in Neural Information Processing System… find
  10. Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Qiuxia Li, and Jun Zhao. 2024. Tug-of-war between knowledge: Exploring and resolving knowledge conflicts in retrieval-augmented language models. In Proceedings of the 2024 Joint International Conference on Computational Lingui…
  11. Ehsan Kamalloo, Nouha Dziri, Charles Clarke, and Davood Rafiei. 2023. Evaluating open-domain question answering in the era of large language models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5591–5606, Toronto, Canada. A…
  12. Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean-Bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penchev, Gaël Liu,… find
  13. Anant Khandelwal, Manish Gupta, and Puneet Agrawal. 2025. Cocoa: Confidence and context-aware adaptive decoding for resolving knowledge conflicts in large language models. CoRR, abs/2508.17670. find
  14. Jungyeon Lee, Kangmin Lee, and Taeuk Kim. 2025. MAGIC: A multi-hop and graph-based benchmark for inter-context conflicts in retrieval-augmented generation. CoRR, abs/2507.21544. find
  15. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Proc…
  16. Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, and Huan Liu. 2024. From generation to judgment: Opportunities and challenges of llm-as-a-judge. CoRR, abs/2411.16594. find
  17. Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. Lost in the middle: How language models use long contexts. Trans. Assoc. Comput. Linguistics, 12:157–173.
  18. Shayne Longpre, Kartik Perisetla, Anthony Chen, Nikhil Ramesh, Chris DuBois, and Sameer Singh. 2021. Entity-based knowledge conflicts in question answering. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Re…
  19. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (V… find
  20. Sara Marjanovic, Haeun Yu, Pepa Atanasova, Maria Maistro, Christina Lioma, and Isabelle Augenstein. 2024. DYNAMICQA: tracing internal knowledge conflicts in language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, pages 143… find
  21. Francesco Ortu, Zhijing Jin, Diego Doimo, Mrinmaya Sachan, Alberto Cazzaniga, and Bernhard Schölkopf. 2024. Competition of mechanisms: Tracing how language models handle facts and counterfactuals. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: L…
  22. Quang Pham, Hoang Ngo, Anh Tuan Luu, and Dat Quoc Nguyen. 2024. Who’s who: Large language models meet knowledge conflicts in practice. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, pages 10142–10151. Association for Computational… find
  23. Dan Shi, Renren Jin, Tianhao Shen, Weilong Dong, Xinwei Wu, and Deyi Xiong. 2024a. IRCAN: mitigating knowledge conflicts in LLM generation via identifying and reweighting context-aware neurons. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processin… find
  24. Weijia Shi, Xiaochuang Han, Mike Lewis, Yulia Tsvetkov, Luke Zettlemoyer, and Wen-tau Yih. 2024b. Trusting your evidence: Hallucinate less with context-aware decoding. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language…
  25. Zhaochen Su, Jun Zhang, Xiaoye Qu, Tong Zhu, Yanshu Li, Jiashuo Sun, Juntao Li, Min Zhang, and Yu Cheng. 2024. Conflictbank: A benchmark for evaluating the influence of knowledge conflicts in llms. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Proce… find
  26. Yi Sui, Chaozhuo Li, Chen Zhang, Dawei song, and Qiuchi Li. 2025. Bridging external and parametric knowledge: Mitigating hallucination of llms with shared-private semantic synergy in dual-stream knowledge. CoRR, abs/2506.06240. find
  27. Kaiser Sun, Fan Bai, and Mark Dredze. 2025. Task matters: Knowledge requirements shape llm responses to context-memory conflict. CoRR, abs/2506.06485.
  28. Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, and Xueqi Cheng. 2024. Blinded by generated contexts: How language models merge generated and retrieved contexts when knowledge conflicts? In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo…
  29. Ruixiang Tang, Yu-Neng Chuang, and Xia Hu. 2023. The science of detecting llm-generated texts. CoRR, abs/2303.07205. — [arXiv:2303.07205](https://arxiv.org/abs/2303.07205) find
  30. Wei Tang, Yixin Cao, Yang Deng, Jiahao Ying, Bo Wang, Yizhe Yang, Yuyue Zhao, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, and Yong Liao. 2025. Evowiki: Evaluating llms on evolving knowledge. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Paper… find
  31. Zineddine Tighidet, Andrea Mogini, Hedi Ben-younes, Jiali Mei, Patrick Gallinari, and Benjamin Piwowarski. 2025. Context copying modulation: The role of entropy neurons in managing parametric and contextual knowledge conflicts. Preprint, arXiv:2509.10663. find
  32. Hitesh Wadhwa, Rahul Seetharaman, Somyaa Aggarwal, Reshmi Ghosh, Samyadeep Basu, Soundararajan Srinivasan, Wenlong Zhao, Shreyas Chaudhari, and Ehsan Aghazadeh. 2024. From rags to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries.… — [arXiv:2406.12824](https://arxiv.org/abs/2406.12824) find
  33. Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, and Sercan Ö. Arik. 2025a. Astute RAG: overcoming imperfect retrieval augmentation and knowledge conflicts for large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), A…
  34. Yike Wang, Shangbin Feng, Heng Wang, Weijia Shi, Vidhisha Balachandran, Tianxing He, and Yulia Tsvetkov. 2023. Resolving knowledge conflicts in large language models. CoRR, abs/2310.00935.
  35. Yilin Wang, Heng Wang, Yuyang Bai, and Minnan Luo. 2025b. Continuously steering llms sensitivity to contextual knowledge with proxy models. CoRR, abs/2508.19720. find
  36. Yuhao Wang, Ruiyang Ren, Yucheng Wang, Wayne Xin Zhao, Jing Liu, Hua Wu, and Haifeng Wang. 2025c. Unveiling knowledge utilization mechanisms in llm-based retrieval-augmented generation. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval… find
  37. Kam-Fai Wong, and Pasquale Minervini. 2025. Steering knowledge selection behaviours in llms via sae-based representation engineering. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2025… find
  38. Yuqing Wang and Yun Zhao. 2024. TRAM: benchmarking temporal reasoning for large language models. In Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024, pages 6389–6415. Association for Computational Linguistics. find
  39. Jerry W. Wei, Da Huang, Yifeng Lu, Denny Zhou, and Quoc V. Le. 2023. Simple synthetic data reduces sycophancy in large language models. CoRR, abs/2308.03958. find
  40. Wikidata contributors. 2025. Wikidata. https://www.wikidata.org/. ↗
  41. Wenxuan Zhou, Sheng Zhang, Hoifung Poon, and Muhao Chen. 2023. Context-faithful prompting for large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, pages 14544– 14556. Association for Computational Linguistics.
  42. Rongwu Xu, Zehan Qi, Zhijiang Guo, Cunxiang Wang, Hongru Wang, Yue Zhang, and Wei Xu. 2024. Knowledge conflicts for llms: A survey. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Miami, FL, USA, November 12-16, 2024, pages 8541–8565. Associatio…
  43. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jian Yang, Jiaxi Yang, Jingren Zhou, Jun… — Qwen3 Technical Report
  44. Evelyn Yee, Alice Li, Chenyu Tang, Yeon Ho Jung, Ramamohan Paturi, and Leon Bergen. 2024. Dissociation of faithful and unfaithful reasoning in llms. CoRR, abs/2405.15092. — [arXiv:2405.15092](https://arxiv.org/abs/2405.15092) find
  45. Qinan Yu, Jack Merullo, and Ellie Pavlick. 2023. Characterizing mechanisms for factual recall in language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 9924–9959. Association for Computational Ling… find
  46. Michael J. Q. Zhang and Eunsol Choi. 2023. Mitigating temporal misalignment by discarding outdated facts. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023, pages 14213– 14226. Association for Computational Linguisti… find
  47. Yu Zhao, Alessio Devoto, Giwon Hong, Xiaotang Du, Aryo Pradipta Gema, Hongru Wang, Xuanli He, find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wallat-2026-when-facts-change-temporal-knowledge/