@inproceedings{jamialahmadi-etal-2025-balcony,
    title = "Balcony: A Lightweight Approach to Dynamic Inference of Generative Language Models",
    author = "Jamialahmadi, Benyamin  and
      Kavehzadeh, Parsa  and
      Rezagholizadeh, Mehdi  and
      Farinneya, Parsa  and
      Rajabzadeh, Hossein  and
      Jafari, Aref  and
      Chen, Boxing  and
      Tahaei, Marzieh S.",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1263/",
    pages = "24864--24878",
    ISBN = "979-8-89176-332-6",
    abstract = "Deploying large language models (LLMs) in real-world applications is often hindered by strict computational and latency constraints. While dynamic inference offers the flexibility to adjust model behavior based on varying resource budgets, existing methods are frequently limited by hardware inefficiencies or performance degradation. In this paper, we introduce Balcony, a simple yet highly effective framework for depth-based dynamic inference. By freezing the pretrained LLM and inserting additional transformer layers at selected exit points, Balcony maintains the full model{'}s performance while enabling real-time adaptation to different computational budgets. These additional layers are trained using a straightforward self-distillation loss, aligning the sub-model outputs with those of the full model. This approach requires significantly fewer training tokens and tunable parameters, drastically reducing computational costs compared to prior methods. When applied to the LLaMA3-8B model, using only 0.2{\%} of the original pretraining data, Balcony achieves minimal performance degradation while enabling significant speedups. Remarkably, we show that Balcony outperforms state-of-the-art methods such as Flextron and Layerskip on multiple models at various scales, as well as other leading compression techniques across a variety of benchmarks."
}