@inproceedings{govindan-etal-2025-temporal,
    title = "Temporal Alignment of Time Sensitive Facts with Activation Engineering",
    author = "Govindan, Sanjay  and
      Pagnucco, Maurice  and
      Song, Yang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.404/",
    doi = "10.18653/v1/2025.findings-emnlp.404",
    pages = "7640--7657",
    ISBN = "979-8-89176-335-7",
    abstract = "Large Language Models (LLMs) are trained on diverse and often conflicting knowledge spanning multiple domains and time periods. Some of this knowledge is only valid within specific temporal contexts, such as answering the question, ``Who is the President of the United States in 2022?'' Ensuring LLMs generate time-appropriate responses is crucial for maintaining relevance and accuracy. In this work we explore activation engineering as a method for temporally aligning LLMs to improve factual recall without any training. Activation engineering has predominantly been used to steer subjective and qualitative outcomes such as toxicity or behavior. Our research is one of few that uncovers the bounds of activation engineering on objective outcomes. We explore an activation engineering technique to anchor LLaMA 2, LLaMA 3.1, Qwen 2 and Gemma 2 to specific points in time and examine the effects of varying injection layers and prompting strategies. Our experiments demonstrate up to a 44{\%} and 16{\%} improvement in relative and explicit prompting respectively, achieving comparable performance to the fine-tuning method proposed by Zhao et al. (2024). Notably, for LLaMA 2 and LLaMA 3.1 our approach achieves similar results to the fine-tuning baseline while being significantly more computationally efficient and requiring no pre-aligned datasets."
}