Inseq: An Interpretability Toolkit For Sequence Generation Models

Sarti Gabriele, Feldhus Nils, Sickert Ludwig, Van Der Wal Oskar, Nissim Malvina, Bisazza Arianna. Proceedings of ACL System Demonstrations 2023

[Paper]    
Applications Ethics And Bias GPT Interpretability And Explainability Model Architecture Pretraining Methods Reinforcement Learning Tools Transformer

Past work in natural language processing interpretability focused mainly on popular classification tasks while largely overlooking generation settings, partly due to a lack of dedicated tools. In this work, we introduce Inseq, a Python library to democratize access to interpretability analyses of sequence generation models. Inseq enables intuitive and optimized extraction of models’ internal information and feature importance scores for popular decoder-only and encoder-decoder Transformers architectures. We showcase its potential by adopting it to highlight gender biases in machine translation models and locate factual knowledge inside GPT-2. Thanks to its extensible interface supporting cutting-edge techniques such as contrastive feature attribution, Inseq can drive future advances in explainable natural language generation, centralizing good practices and enabling fair and reproducible model evaluations.

Similar Work