Debias-SparseGPT is introduced, a post-training pruning method incorporating representational debiasing using a second-order term defined over demographically contrasting inputs that consistently reduces pruning-induced bias compared to SparseGPT while preserving model perplexity and zero-shot accuracy.
Abstract
Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). However, recent studies show that weight sparsification methods, such as SparseGPT, can amplify existing biases in models, with outputs varying significantly depending on persona cues in the prompt. In this paper, we introduce Debias-SparseGPT, a post-training pruning method incorporating representational debiasing using a second-order term defined over demographically contrasting inputs. We perform empirical validation of our method over a wide range of generative LLMs. Across models and sparsity regimes (25%, 50%, and structured 2:4 sparsity), Debias-SparseGPT consistently reduces pruning-induced bias compared to SparseGPT while preserving model perplexity and zero-shot accuracy. Under the most restrictive 2:4 structured sparsity pattern, which most aggressively degrades model quality, augmenting the calibration set with long-context, content-rich examples further improves both downstream performance and fairness. Overall, Debias-SparseGPT advances the bias-performance trade-off while preserving the computational efficiency of sparse models.
This work forms the pruning objective as a cardinality-constrained binary quadratic program that explicitly models cross-unit dependencies in the reconstruction error, and develops a greedy interaction algorithm based on dependency-aware marginal costs to optimize unit selection.
Si-Cheng Xu, Hao Shi, Wei Zhang et al.· 0 citations
Activation sparsity speeds up large language model (LLM) inference by setting unimportant activations to zero so that the corresponding computations can be skipped. Existing training-free methods, however, make different trade-offs: threshold-based methods such as TEAL adapt the sparsity level to each token but do not...
Extending LILA to dynamically allocate sparsity budgets via KS-scores yields state-of-the-art generative preservation at moderate compression, while uncovering fundamental single-layer architectural bottlenecks at higher compression regimes.
Sankar Behera, Dhruv Singh, Anshika Agnihotri et al.· 1 citation
A systematic study of how pruning affects SAE behavior is presented and theoretically shows that, for a fixed SAE, its impact is governed by perturbation energy, a covariance-weighted norm.
Suchit Gupte, Xue-Ru Zhang, M. Khalili· 0 citations
This work characterize the effect of a residual-stream perturbation through both its activation covariance and the local sensitivity of the model output, and derives a tractable spectral upper bound that reduces subspace selection to an eigendecomposition of a sensitivity-weighted covariance matrix, retaining the effic...
Chayne Thrash, Ke Chen, Soheil Kolouri· arXiv.org· 0 citations
This work introduces StructTune1, a PEFT method that uses entire rows or columns as basic units for identifying task-relevant sparse components and develops a sensitivity-based framework to efficiently identify task-relevant weight structures without full fine-tuning.
Yu-Yang Liu, Lai-Man Po, Kwok-Wai Cheung et al.· Transactions of the Associat...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 19, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.