No article text was recorded for this version.
compression-induced bias
Version 2 of 2142 papers258 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Does Compression Exacerbate Large Language Models' Social Bias?
- Blog: A Fair Loss Function for Network Pruning
- Blog: Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions
- Blog: Properties Of Winning Tickets On Skin Lesion Classification
- Blog: Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions
- Blog: FairGRAPE: Fairness-Aware GRAdient Pruning mEthod for Face Attribute Classification
- Blog: Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures
- Blog: Unmasking the Hidden Fairness, Bias, and Safety Costs of Compression with Mixture-of-Expert Models
- Blog: The Impact of Inference Acceleration on Bias of LLMs
- Blog: Gone With the Bits: Benchmarking Bias in Facial Phenotype Degradation Under Low-Rate Neural Compression
- Blog: Is the Lottery Fair? Evaluating Winning Tickets Across Demographics
- Blog: What Do Compressed Multilingual Machine Translation Models Forget?
- Blog: Coupling Fairness and Pruning in a Single Run: a Bi-level Optimization Perspective
- Blog: Bridging Fairness and Environmental Sustainability in Natural Language Processing
- Blog: Gender Bias Amplification During Speed-Quality Optimization in Neural Machine Translation
- Blog: Why Knowledge Distillation Amplifies Gender Bias and How to Mitigate from the Perspective of DistilBERT
- Blog: What Do Compressed Multilingual Machine Translation Models Forget?
- Blog: Compressed models for co-reference resolution: enhancing efficiency with debiased word embeddings
- Blog: Characterising Bias in Compressed Models
- Blog: Efficient DNN-Powered Software with Fair Sparse Models
- Blog: The Impact of Inference Acceleration on Bias of LLMs
- Blog: Balancing Act: Constraining Disparate Impact in Sparse Models
- Blog: You Never Know: Quantization Induces Inconsistent Biases in Vision-Language Foundation Models
- Blog: Bridging Fairness and Environmental Sustainability in Natural Language Processing
- Blog: Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models
- Blog: Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation
- Blog: A Comparative Study on the Impact of Model Compression Techniques on Fairness in Language Models
- Blog: FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification
- Blog: The Effect of Model Compression on Fairness in Facial Expression Recognition
- Blog: HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization
- Blog: Are Compressed Language Models Less Subgroup Robust?
- Blog: Meta-Learning Sparse Implicit Neural Representations
- Blog: Selective Brain Damage: Measuring the Disparate Impact of Model Pruning
- Blog: Evaluation of Social Biases in Recent Large Pre-Trained Models
- Blog: Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression
- Blog: What Causes a Disparate Impact in a Quantized Model?
- Blog: Prune Responsibly
- Blog: Adversarial Examples Generation for Reducing Implicit Gender Bias in Pre-trained Models
- Blog: Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging
- Blog: Balancing Act: Constraining Disparate Impact in Sparse Models
- Blog: Efficient Methods for Natural Language Processing: A Survey
- Blog: Addressing Bias Through Ensemble Learning and Regularized Fine-Tuning
- Blog: Understanding the Effect of Model Compression on Social Bias in Large Language Models
- Blog: Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks
- Blog: Is a Prestigious Job the same as a Prestigious Country? A Case Study on Multilingual Sentence Embeddings and European Countries
- Blog: Going Beyond Classification Accuracy Metrics in Model Compression
- Blog: Can Model Compression Improve NLP Fairness
- Blog: Pruning has a disparate impact on model accuracy
- Blog: Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures
- Blog: Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
- Blog: Understanding the Effect of Model Compression on Social Bias in Large Language Models
- Blog: Pruning has a disparate impact on model accuracy
- Blog: Reliable Model Compression via Label-Preservation-Aware Loss Functions
- Blog: A Survey for Efficient Open Domain Question Answering
- Blog: FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models
- Blog: Towards Fairness-aware Adversarial Network Pruning
- Blog: Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Neural Networks
- Blog: How Many Bits Does it Take to Quantize Your Neural Network?
- Blog: Robustness Challenges in Model Distillation and Pruning for Natural Language Understanding
- Blog: Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
Showing 60 of 142 papers.
History & citation
Current · Permanent link
- The Disparate Impact of Neural Network Compression merged into this direction (100% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_compression_induced_bias_10382b51,
title = {compression-induced bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/compression-induced-bias/rdr_10382b5153714e0f865f7c64342588fd},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 2, frozen text):
@misc{lacuna_compression_induced_bias_10382b51_v2,
title = {compression-induced bias},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/compression-induced-bias/rdr_10382b5153714e0f865f7c64342588fd/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-22},
}