paper-with-me

홈 › Papers

Teacher's pet: understanding and mitigating biases in distillation

2021-06-19 · Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar

Knowledge distillation is widely used as a means of improving the performance of a relatively simple student model using the predictions from a complex teacher model. Several works have shown that distillation significantly boosts the student's overall performance; however, are these gains uniform across all data subgroups? In this paper, we show that distillation can harm performance on certain subgroups, e.g., classes with few associated samples. We trace this behaviour to errors made by the teacher distribution being transferred to and amplified by the student model. To mitigate this problem, we present techniques which soften the teacher influence for subgroups where it is less reliable. Experiments on several image classification benchmarks show that these modifications of distillation maintain boost in overall accuracy, while additionally ensuring improvement in subgroup performance.

📄 PDF Abstract BibTeX arXiv:2106.10494

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationKnowledge Distillation

Similar Papers 제목 키워드 기반

Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation

2026-05-19 · Bing Wang, Shaotian Yan, Chen Shen, kaiyuan liu 외 arxiv

Large language models (LLMs) have achieved remarkable success in complex reasoning tasks via long chain-of-thought (CoT), yet their immense computational overhead hinders real-world deployment. LLM reasoning distillation…

"The Whole Is Greater Than the Sum of Its Parts": A Compatibility-Aware Multi-Teacher CoT Distillation Framework

2026-01-20 · Jin Cui, Jiaqi Guo, Ruixuan Yang, Jiayi Lu 외 arxiv

Chain-of-Thought (CoT) reasoning empowers Large Language Models (LLMs) with remarkable capabilities but typically requires prohibitive parameter scales. CoT distillation has emerged as a promising paradigm to transfer re…

Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer

2025-09-28 · Simon Schrodi, Elias Kempf, Fazl Barez, Thomas Brox arxiv

Language models can transfer hidden biases during distillation. For example, a teacher that "likes owls" can make its student "like owls" too, even when the training data consists only of lists of numbers. This surprisin…

Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal

2022-03-23 · Findings (ACL) 2022 5 · Umang Gupta, Jwala Dhamala, Varun Kumar, Apurv Verma 외

Language models excel at generating coherent text, and model compression techniques such as knowledge distillation have enabled their use in resource-constrained settings. However, these models can be biased in multiple …

counterfactualFairnessKnowledge DistillationModel Compression+1

Critique-Guided Distillation: Improving Supervised Fine-tuning via Better Distillation

2025-05-16 · Berkcan Kapusuzoglu, Supriyo Chakraborty, Chia-Hsuan Lee, Sambit Sahu

Supervised fine-tuning (SFT) using expert demonstrations often suffer from the imitation problem, where the model learns to reproduce the correct responses without \emph{understanding} the underlying rationale. To addres…

MathMMLUTriplet