TopEx: Topic-based Explanations for Model Comparison
Not on the map. Why?
Abstract (arXiv)
Meaningfully comparing language models is challenging with current explanation methods. Current explanations are overwhelming for humans due to large vocabularies or incomparable across models. We present TopEx, an explanation method that enables a level playing field for comparing language models via model-agnostic topics. We demonstrate how TopEx can identify similarities and differences between DistilRoBERTa and GPT-2 on a variety of NLP tasks.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 6 of its 16 references that are in the map. First posted on arXiv 1 Jun 2023.
Builds on
6 of 16 references.
References · 6
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
- 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 479
- 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 155
Built on by
Citing papers per year: 2023: 1; 2024: 2.
3 papers.