---
title: "BlackboxNLP Workshop on Analyzing and Interpreting Neural"
description: "All 37 papers of BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2022, the most cited first; those with our…"
canonical: "https://research.elamur.ai/free/en/venues/blackboxnlp/2022/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/blackboxnlp/2022/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [BlackboxNLP Workshop on Analyzing and…](https://md.research.elamur.ai/free/en/venues/blackboxnlp/) / [2022](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2022/) / papers

# BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2022: all accepted papers

37 papers · the most cited first · [← BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2022](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2022/)

1. **[DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models ↗](https://aclanthology.org/2022.blackboxnlp-1.28/)**Royi Rassin, Shauli Ravfogel, Yoav Goldberg*39 citations*
2. **[Probing Pretrained Models of Source Codes ↗](https://aclanthology.org/2022.blackboxnlp-1.31/)**Sergey Troshin, Nadezhda Chirkova*21 citations*
3. **[Probing GPT-3's Linguistic Knowledge on Semantic Tasks ↗](https://aclanthology.org/2022.blackboxnlp-1.24/)**Lining Zhang, Mengchen Wang, Liben Chen et al.*11 citations*
4. **[On the Compositional Generalization Gap of In-Context Learning ↗](https://aclanthology.org/2022.blackboxnlp-1.22/)**Arian Hosseini, Ankit Vani, Dzmitry Bahdanau et al.*10 citations*
5. **[It Is Not Easy To Detect Paraphrases: Analysing Semantic Similarity With Antonyms and Negation Using the New SemAntoNeg Benchmark ↗](https://aclanthology.org/2022.blackboxnlp-1.20/)**Teemu Vahtola, Mathias Creutz, Jörg Tiedemann*9 citations*
6. **[Explaining Translationese: why are Neural Classifiers Better and what do they Learn? ↗](https://aclanthology.org/2022.blackboxnlp-1.23/)**Kwabena Amponsah-Kaakyire, Daria Pylypenko, Josef Genabith et al.*7 citations*
7. **[Are Multilingual Sentiment Models Equally Right for the Right Reasons? ↗](https://aclanthology.org/2022.blackboxnlp-1.11/)**Rasmus Jørgensen, Fiammetta Caccavale, Christian Igel et al.*6 citations*
8. **[Sparse Interventions in Language Models with Differentiable Masking ↗](https://aclanthology.org/2022.blackboxnlp-1.2/)**Nicola De Cao, Leon Schmid, Dieuwke Hupkes et al.*6 citations*
9. **[Decomposing Natural Logic Inferences for Neural NLI](https://md.research.elamur.ai/free/en/papers/rozanova-2022-decomposing-natural-logic-inferences-neural/)**Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan et al.*5 citations · our summary*
10. **[Investigating the Characteristics of a Transformer in a Few-Shot Setup: Does Freezing Layers in RoBERTa Help? ↗](https://aclanthology.org/2022.blackboxnlp-1.19/)**Digvijay Ingle, Rishabh Tripathi, Ayush Kumar et al.*5 citations*
11. **[Garden Path Traversal in GPT-2 ↗](https://aclanthology.org/2022.blackboxnlp-1.25/)**William Jurayj, William Rudman, Carsten Eickhoff*4 citations*
12. **[Practical Benefits of Feature Feedback Under Distribution Shift ↗](https://aclanthology.org/2022.blackboxnlp-1.29/)**Anurag Katakkar, Clay H. Yoo, Weiqin Wang et al.*4 citations*
13. **[Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information ↗](https://aclanthology.org/2022.blackboxnlp-1.18/)**Isar Nejadgholi, Esma Balkir, Kathleen Fraser et al.*4 citations*
14. **[Human Ratings Do Not Reflect Downstream Utility: A Study of Free-Text Explanations for Model Predictions ↗](https://aclanthology.org/2022.blackboxnlp-1.14/)**Jenny Kunz, Martin Jirenius, Oskar Holmström et al.*3 citations*
15. **[Probing with Noise: Unpicking the Warp and Weft of Embeddings ↗](https://aclanthology.org/2022.blackboxnlp-1.34/)**Filip Klubicka, John Kelleher*3 citations*
16. **[Understanding Domain Learning in Language Models Through Subpopulation Analysis ↗](https://aclanthology.org/2022.blackboxnlp-1.16/)**Zheng Zhao, Yftah Ziser, Shay B. Cohen*3 citations*
17. **[Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering ↗](https://aclanthology.org/2022.blackboxnlp-1.35/)**Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa*2 citations*
18. **[Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines ↗](https://aclanthology.org/2022.blackboxnlp-1.5/)**Kiron Deb, Xuan Zhang, Kevin Duh*2 citations*
19. **[Post-hoc analysis of Arabic transformer models ↗](https://aclanthology.org/2022.blackboxnlp-1.8/)**Ahmed Abdelali, Nadir Durrani, Fahim Dalvi et al.*2 citations*
20. **[Probing for Understanding of English Verb Classes and Alternations in Large Pre-trained Language Models ↗](https://aclanthology.org/2022.blackboxnlp-1.12/)**David Yi, James Bruno, Jiayu Han et al.*2 citations*
21. **[Testing Pre-trained Language Models' Understanding of Distributivity via Causal Mediation Analysis ↗](https://aclanthology.org/2022.blackboxnlp-1.26/)**Pangbo Ban, Yifan Jiang, Tianran Liu et al.*2 citations*
22. **[A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition ↗](https://aclanthology.org/2022.blackboxnlp-1.36/)**Darcey Riley, David Chiang*1 citation*
23. **[A Minimal Model for Compositional Generalization on gSCAN ↗](https://aclanthology.org/2022.blackboxnlp-1.1/)**Alice Hein, Klaus Diepold*1 citation*
24. **[Analyzing Gender Translation Errors to Identify Information Flows between the Encoder and Decoder of a NMT System ↗](https://aclanthology.org/2022.blackboxnlp-1.13/)**Guillaume Wisniewski, Lichao Zhu, Nicolas Ballier et al.*1 citation*
25. **[Analyzing the Representational Geometry of Acoustic Word Embeddings ↗](https://aclanthology.org/2022.blackboxnlp-1.15/)**Badr Abdullah, Dietrich Klakow*1 citation*
26. **[Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification ↗](https://aclanthology.org/2022.blackboxnlp-1.30/)**Ruixuan Tang, Hanjie Chen, Yangfeng Ji*1 citation*
27. **[Intermediate Entity-based Sparse Interpretable Representation Learning ↗](https://aclanthology.org/2022.blackboxnlp-1.17/)**Diego Garcia-Olano, Yasumasa Onoe, Joydeep Ghosh et al.*1 citation*
28. **[Is It Smaller Than a Tennis Ball? Language Models Play the Game of Twenty Questions ↗](https://aclanthology.org/2022.blackboxnlp-1.7/)**Maxime De Bruyn, Ehsan Lotfi, Jeska Buhmann et al.*1 citation*
29. **[Sentence Ambiguity, Grammaticality and Complexity Probes ↗](https://aclanthology.org/2022.blackboxnlp-1.4/)**Sunit Bhattacharya, Vilém Zouhar, Ondrej Bojar*1 citation*
30. **[Using Roark-Hollingshead Distance to Probe BERT's Syntactic Competence ↗](https://aclanthology.org/2022.blackboxnlp-1.27/)**Jingcheng Niu, Wenjie Lu, Eric Corlett et al.*1 citation*
31. **[Where's the Learning in Representation Learning for Compositional Semantics and the Case of Thematic Fit ↗](https://aclanthology.org/2022.blackboxnlp-1.3/)**Mughilan Muthupari, Samrat Halder, Asad Sayeed et al.*1 citation*
32. **[Controlling for Stereotypes in Multimodal Language Model Evaluation ↗](https://aclanthology.org/2022.blackboxnlp-1.21/)**Manuj Malik, Richard Johansson
33. **[How (Un)Faithful is Attention? ↗](https://aclanthology.org/2022.blackboxnlp-1.10/)**Hessam Amini, Leila Kosseim
34. **[Probing the representations of named entities in Transformer-based Language Models ↗](https://aclanthology.org/2022.blackboxnlp-1.32/)**Stefan Schouten, Peter Bloem, Piek Vossen
35. **[Revisit Systematic Generalization via Meaningful Learning ↗](https://aclanthology.org/2022.blackboxnlp-1.6/)**Ning Shi, Boxin Wang, Wei Wang et al.
36. **[Universal Evasion Attacks on Summarization Scoring ↗](https://aclanthology.org/2022.blackboxnlp-1.9/)**Wenchuan Mu, Kwan Hui Lim
37. **[Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation ↗](https://aclanthology.org/2022.blackboxnlp-1.37/)**Oleg Serikov, Vitaly Protasov, Ekaterina Voloshina et al.
- [← back to](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2022/) — BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2022