BlackboxNLP@EMNLP

Publications

2023

Stefan Arnold, Nils Kemmerzell, Annika Schreiner
Disentangling the Linguistic Competence of Privacy-Preserving BERT. BlackboxNLP@EMNLP (2023)
Chandan Singh, John X. Morris, Jyoti Aneja, Alexander M. Rush, Jianfeng Gao
Explaining Data Patterns in Natural Language with Language Models. BlackboxNLP@EMNLP (2023)
Abhijith Chintam, Rahel Beloch, Willem H. Zuidema, Michael Hanna, Oskar van der Wal
Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model. BlackboxNLP@EMNLP (2023)
David Kletz, Pascal Amsili, Marie Candito
The Self-Contained Negation Test Set. BlackboxNLP@EMNLP (2023)
Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2023, Singapore, December 7, 2023 BlackboxNLP@EMNLP (2023)
Aishik Chakraborty, Jackie C. K. Cheung, Timothy J. O'Donnell
Systematic Generalization by Finetuning? Analyzing Pretrained Language Models Using Constituency Tests. BlackboxNLP@EMNLP (2023)
Chenxin Liu, Emmanuele Chersoni
On Quick Kisses and How to Make Them Count: A Study on Event Construal in Light Verb Constructions with BERT. BlackboxNLP@EMNLP (2023)
Neel Nanda, Andrew Lee, Martin Wattenberg
Emergent Linear Representations in World Models of Self-Supervised Sequence Models. BlackboxNLP@EMNLP (2023)
Hao Sun, John Hewitt
Character-Level Chinese Backpack Language Models. BlackboxNLP@EMNLP (2023)
Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Daniel Grzenda, Nathaniel Hudson, André Bauer, Kyle Chard, Ian T. Foster
Memory Injections: Correcting Multi-Hop Reasoning Failures During Inference in Transformer-Based Language Models. BlackboxNLP@EMNLP (2023)
Nirmalendu Prakash, Roy Ka-Wei Lee
Layered Bias: Interpreting Bias in Pretrained Large Language Models. BlackboxNLP@EMNLP (2023)
Shunjie Wang, Shane Steinert-Threlkeld
Evaluating Transformer's Ability to Learn Mildly Context-Sensitive Languages. BlackboxNLP@EMNLP (2023)
Deanna DeCarlo, William Palmer, Michael Wilson, Bob Frank
NPIs Aren't Exactly Easy: Variation in Licensing across Large Language Models. BlackboxNLP@EMNLP (2023)
Yan Cong, Emmanuele Chersoni, Yu-Yin Hsu, Philippe Blache
Investigating the Effect of Discourse Connectives on Transformer Surprisal: Language Models Understand Connectives, Even So They Are Surprised. BlackboxNLP@EMNLP (2023)
Natalia Flechas Manrique, Wanqian Bao, Aurélie Herbelot, Uri Hasson
Enhancing Interpretability Using Human Similarity Judgements to Prune Word Embeddings. BlackboxNLP@EMNLP (2023)
Juanhe (TJ) Tan
Causal Abstraction for Chain-of-Thought Reasoning in Arithmetic Word Problems. BlackboxNLP@EMNLP (2023)
Isabelle Lorge, Janet B. Pierrehumbert
Not Wacky vs. Definitely Wacky: A Study of Scalar Adverbs in Pretrained Language Models. BlackboxNLP@EMNLP (2023)
Yichu Zhou, Vivek Srikumar
METAPROBE: A Representation- and Task-Agnostic Probe. BlackboxNLP@EMNLP (2023)
Antoine Chaffin, Julien Delaunay
"Honey, Tell Me What's Wrong", Global Explanation of Textual Discriminative Models through Cooperative Generation. BlackboxNLP@EMNLP (2023)
Jacob K. Johnson, Ana Marasovic
How Much Consistency Is Your Accuracy Worth? BlackboxNLP@EMNLP (2023)
Judith Sieker, Sina Zarrieß
When Your Language Model Cannot Even Do Determiners Right: Probing for Anti-Presuppositions and the Maximize Presupposition! Principle. BlackboxNLP@EMNLP (2023)
Henning Bartsch, Ole Jorgensen, Domenic Rosati, Jason Hoelscher-Obermaier, Jacob Pfau
Self-Consistency of Large Language Models under Ambiguity. BlackboxNLP@EMNLP (2023)
Dmitry Nikolaev, Sebastian Padó
Investigating Semantic Subspaces of Transformer Sentence Embeddings through Linear Structural Probing. BlackboxNLP@EMNLP (2023)
Sunit Bhattacharya, Ondrej Bojar
Unveiling Multilinguality in Transformer Models: Exploring Language Specificity in Feed-Forward Networks. BlackboxNLP@EMNLP (2023)
Akshat Gupta
Probing Quantifier Comprehension in Large Language Models: Another Example of Inverse Scaling. BlackboxNLP@EMNLP (2023)
Timothee Mickus, Raúl Vázquez
Why Bother with Geometry? On the Relevance of Linear Decompositions of Transformer Embeddings. BlackboxNLP@EMNLP (2023)
Tanja Baeumel, Soniya Vijayakumar, Josef van Genabith, Guenter Neumann, Simon Ostermann
Investigating the Encoding of Words in BERT's Neurons Using Feature Textualization. BlackboxNLP@EMNLP (2023)
Anthony M. Colas, Jun Araki, Zhengyu Zhou, Bingqing Wang, Zhe Feng
Knowledge-Grounded Natural Language Recommendation Explanation. BlackboxNLP@EMNLP (2023)
Jonas Groschwitz
Introducing VULCAN: A Visualization Tool for Understanding Our Models and Data by Example. BlackboxNLP@EMNLP (2023)
Jing Huang, Atticus Geiger, Karel D'Oosterlinck, Zhengxuan Wu, Christopher Potts
Rigorously Assessing Natural Language Explanations of Neurons. BlackboxNLP@EMNLP (2023)

2022