Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Dongwon Jung, Hadi Askari, Wenxuan Zhou, Zhe Zhao, Muhao Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Pretrained Large Language Models (LLMs) achieve strong performance across a wide range of tasks, yet exhibit substantial variability in the various layers' training quality with respect to specific downstream applications, limiting their downstream performance. It is therefore critical to estimate layer-wise training quality in a manner that accounts for both model architecture and training data. However, existing approaches predominantly rely on model-centric heuristics (such as spectral statistics, outlier detection, or uniform allocation) while overlooking the influence of data. To address these limitations, we propose **LayerIF**, a data-driven framework that leverages *Influence Functions* to quantify the training quality of individual layers in a principled and task-sensitive manner. By isolating each layer's gradients and measuring the sensitivity of the validation loss to training examples by computing layer-wise influences, we derive data-driven estimates of layer importance. Notably, our method produces *task-specific* layer importance estimates for the *same* LLM, revealing how layers specialize for different test-time evaluation tasks. We demonstrate the utility of our scores by leveraging them for two downstream applications: (a) expert allocation in LoRA-MoE architectures and (b) layer-wise sparsity distribution for LLM pruning. Experiments across multiple LLM architectures demonstrate that our model-agnostic, influence-guided allocation leads to consistent gains in task performance.

Online content platforms optimize engagement by providing personalized recommendations to their users. These recommendation systems track and profile users to predict relevant content a user is likely interested in. While the personalized recommendations provide utility to users, the tracking and profiling that enables them poses a privacy issue because the platform might infer potentially sensitive user interests. There is increasing interest in building privacy-enhancing obfuscation approaches that do not rely on cooperation from online content platforms. However, existing obfuscation approaches primarily focus on enhancing privacy but at the same time they degrade the utility because obfuscation introduces unrelated recommendations. We design and implement DeHarpo, an obfuscation approach for YouTube's recommendation system that not only obfuscates a user's video watch history to protect privacy but then also denoises the video recommendations by YouTube to preserve their utility. In contrast to prior obfuscation approaches, DeHarpo adds a denoiser that makes use of a ``secret'' input (i.e., a user's actual watch history) as well as information that is also available to the adversarial recommendation system (i.e., obfuscated watch history and corresponding ``nois`` recommendations). Our large-scale evaluation of DeHarpo shows that it outperforms the state-of-the-art by a factor of 2x in terms of preserving utility for the same level of privacy, while maintaining stealthiness and robustness to de-obfuscation.