Lost in Distillation: A Case Study in Toxicity Modeling
In an era of increasingly large pre-trained language models, knowledge distillation is a powerful tool for transferring information from a large model to a smaller one. In particular, distillation is of tremendous benefit when it comes to real-world constraints such as serving latency or serving at scale. However, a loss of robustness in language understanding may be hidden in the process and not immediately revealed when looking at high-level evaluation metrics. In this work, we investigate the hidden costs: what is “lost in distillation”, especially in regards to identity-based model bias using the case study of toxicity modeling. With reproducible models using open source training sets, we investigate models distilled from a BERT teacher baseline. Using both open source and proprietary big data models, we investigate these hidden performance costs.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge DistillationSimilar Papers 제목 키워드 기반
Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes
Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framewo…
Knowledge DistillationKnowledge GraphsTowards Robust Toxic Content Classification
Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a m…
ClassificationDenoisingGeneral ClassificationIntegrating Pharmacokinetics and Pharmacodynamics Modeling with Quantum Regression for Predicting Herbal Compound Toxicity
Herbal compounds present complex toxicity profiles that are often influenced by both intrinsic chemical properties and pharmacokinetics (PK) governing absorption and clearance. In this study, we develop a quantum regress…
regressionCan Model Compression Improve NLP Fairness
Model compression techniques are receiving increasing attention; however, the effect of compression on model fairness is still under explored. This is the first paper to examine the effect of distillation and pruning on …
FairnessKnowledge DistillationmodelModel CompressionA Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it dif…
Language ModelingLanguage Modelling