---
title: "BlackboxNLP Workshop on Analyzing and Interpreting Neural"
description: "BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2023 — accepted papers: 2 papers in the Elamur Research…"
canonical: "https://research.elamur.ai/free/en/venues/blackboxnlp/2023/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/blackboxnlp/2023/)

[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/) / 2023

# BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2023 — accepted papers

BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2023 is the 2023 edition of the BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, held in Singapore, December 2023 (publisher: Association for Computational Linguistics). The ACL Anthology lists 29 papers of it; our library holds 2 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

📍 [Singapore](https://md.research.elamur.ai/free/en/countries/singapore/) · 🗓 December 2023

[**29** papers in the proceedings](#all) · [**2** works in our library](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2023/#works) · [**11** citations of these works](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2023/#works)

## Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. **[Emergent Linear Representations in World Models of Self-Supervised Sequence Models ↗](https://aclanthology.org/2023.blackboxnlp-1.2/)**Neel Nanda, Andrew Lee, Martin Wattenberg*35 citations*
2. **[Explaining Data Patterns in Natural Language with Language Models ↗](https://aclanthology.org/2023.blackboxnlp-1.3/)**Chandan Singh, John X. Morris, Jyoti Aneja et al.*14 citations*
3. **[Layered Bias: Interpreting Bias in Pretrained Large Language Models ↗](https://aclanthology.org/2023.blackboxnlp-1.22/)**Nirmalendu Prakash, Roy Ka-Wei Lee*11 citations*
4. **[Self-Consistency of Large Language Models under Ambiguity ↗](https://aclanthology.org/2023.blackboxnlp-1.7/)**Henning Bartsch, Ole Jorgensen, Domenic Rosati et al.*10 citations*
5. **[Knowledge-Grounded Natural Language Recommendation Explanation ↗](https://aclanthology.org/2023.blackboxnlp-1.1/)**Anthony Colas, Jun Araki, Zhengyu Zhou et al.*5 citations*
6. **[Evaluating Transformer's Ability to Learn Mildly Context-Sensitive Languages ↗](https://aclanthology.org/2023.blackboxnlp-1.21/)**Shunjie Wang, Shane Steinert-Threlkeld*4 citations*
7. **[Investigating the Effect of Discourse Connectives on Transformer Surprisal: Language Models Understand Connectives, Even So They Are Surprised ↗](https://aclanthology.org/2023.blackboxnlp-1.17/)**Yan Cong, Emmanuele Chersoni, Yu-Yin Hsu et al.*4 citations*
8. **[Memory Injections: Correcting Multi-Hop Reasoning Failures During Inference in Transformer-Based Language Models ↗](https://aclanthology.org/2023.blackboxnlp-1.26/)**Mansi Sakarvadia, Aswathy Ajith, Arham Khan et al.*4 citations*
9. **[Rigorously Assessing Natural Language Explanations of Neurons ↗](https://aclanthology.org/2023.blackboxnlp-1.24/)**Jing Huang, Atticus Geiger, Karel D'Oosterlinck et al.*3 citations*
10. **[When Your Language Model Cannot Even Do Determiners Right: Probing for Anti-Presuppositions and the Maximize Presupposition! Principle](https://md.research.elamur.ai/free/en/papers/sieker-2023-when-your-language-model-cannot/)**Judith Sieker, Sina Zarrieß*3 citations · our summary*

## All accepted papers (29)

The most cited first; 2 with our summary link to their page here, the others to the original.

1. **[Emergent Linear Representations in World Models of Self-Supervised Sequence Models ↗](https://aclanthology.org/2023.blackboxnlp-1.2/)**Neel Nanda, Andrew Lee, Martin Wattenberg*35 citations*
2. **[Explaining Data Patterns in Natural Language with Language Models ↗](https://aclanthology.org/2023.blackboxnlp-1.3/)**Chandan Singh, John X. Morris, Jyoti Aneja et al.*14 citations*
3. **[Layered Bias: Interpreting Bias in Pretrained Large Language Models ↗](https://aclanthology.org/2023.blackboxnlp-1.22/)**Nirmalendu Prakash, Roy Ka-Wei Lee*11 citations*
4. **[Self-Consistency of Large Language Models under Ambiguity ↗](https://aclanthology.org/2023.blackboxnlp-1.7/)**Henning Bartsch, Ole Jorgensen, Domenic Rosati et al.*10 citations*
5. **[Knowledge-Grounded Natural Language Recommendation Explanation ↗](https://aclanthology.org/2023.blackboxnlp-1.1/)**Anthony Colas, Jun Araki, Zhengyu Zhou et al.*5 citations*
6. **[Evaluating Transformer's Ability to Learn Mildly Context-Sensitive Languages ↗](https://aclanthology.org/2023.blackboxnlp-1.21/)**Shunjie Wang, Shane Steinert-Threlkeld*4 citations*
7. **[Investigating the Effect of Discourse Connectives on Transformer Surprisal: Language Models Understand Connectives, Even So They Are Surprised ↗](https://aclanthology.org/2023.blackboxnlp-1.17/)**Yan Cong, Emmanuele Chersoni, Yu-Yin Hsu et al.*4 citations*
8. **[Memory Injections: Correcting Multi-Hop Reasoning Failures During Inference in Transformer-Based Language Models ↗](https://aclanthology.org/2023.blackboxnlp-1.26/)**Mansi Sakarvadia, Aswathy Ajith, Arham Khan et al.*4 citations*
9. **[Rigorously Assessing Natural Language Explanations of Neurons ↗](https://aclanthology.org/2023.blackboxnlp-1.24/)**Jing Huang, Atticus Geiger, Karel D'Oosterlinck et al.*3 citations*
10. **[When Your Language Model Cannot Even Do Determiners Right: Probing for Anti-Presuppositions and the Maximize Presupposition! Principle](https://md.research.elamur.ai/free/en/papers/sieker-2023-when-your-language-model-cannot/)**Judith Sieker, Sina Zarrieß*3 citations · our summary*
11. **[Causal Abstraction for Chain-of-Thought Reasoning in Arithmetic Word Problems ↗](https://aclanthology.org/2023.blackboxnlp-1.12/)**Juanhe (TJ) Tan*2 citations*
12. **[Enhancing Interpretability Using Human Similarity Judgements to Prune Word Embeddings ↗](https://aclanthology.org/2023.blackboxnlp-1.13/)**Natalia Flechas Manrique, Wanqian Bao, Aurelie Herbelot et al.*2 citations*
13. **[Probing Quantifier Comprehension in Large Language Models: Another Example of Inverse Scaling ↗](https://aclanthology.org/2023.blackboxnlp-1.4/)**Akshat Gupta*2 citations*
14. **[Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model ↗](https://aclanthology.org/2023.blackboxnlp-1.29/)**Abhijith Chintam, Rahel Beloch, Willem Zuidema et al.*1 citation*
15. **[Investigating the Encoding of Words in BERT's Neurons Using Feature Textualization ↗](https://aclanthology.org/2023.blackboxnlp-1.20/)**Tanja Baeumel, Soniya Vijayakumar, Josef van Genabith et al.*1 citation*
16. **[On Quick Kisses and How to Make Them Count: A Study on Event Construal in Light Verb Constructions with BERT](https://md.research.elamur.ai/free/en/papers/liu-2023-quick-kisses-how-make-them/)**Chenxin Liu, Emmanuele Chersoni*1 citation · our summary*
17. **[Why Bother with Geometry? On the Relevance of Linear Decompositions of Transformer Embeddings ↗](https://aclanthology.org/2023.blackboxnlp-1.10/)**Timothee Mickus, Raúl Vázquez*1 citation*
18. **[“Honey, Tell Me What's Wrong”, Global Explanation of Textual Discriminative Models through Cooperative Generation ↗](https://aclanthology.org/2023.blackboxnlp-1.6/)**Antoine Chaffin, Julien Delaunay*1 citation*
19. **[Character-Level Chinese Backpack Language Models ↗](https://aclanthology.org/2023.blackboxnlp-1.8/)**Hao Sun, John Hewitt
20. **[Disentangling the Linguistic Competence of Privacy-Preserving BERT ↗](https://aclanthology.org/2023.blackboxnlp-1.5/)**Stefan Arnold, Nils Kemmerzell, Annika Schreiner
21. **[How Much Consistency Is Your Accuracy Worth? ↗](https://aclanthology.org/2023.blackboxnlp-1.19/)**Jacob K. Johnson, Ana Marasović
22. **[Introducing VULCAN: A Visualization Tool for Understanding Our Models and Data by Example ↗](https://aclanthology.org/2023.blackboxnlp-1.15/)**Jonas Groschwitz
23. **[Investigating Semantic Subspaces of Transformer Sentence Embeddings through Linear Structural Probing ↗](https://aclanthology.org/2023.blackboxnlp-1.11/)**Dmitry Nikolaev, Sebastian Padó
24. **[METAPROBE: A Representation- and Task-Agnostic Probe ↗](https://aclanthology.org/2023.blackboxnlp-1.18/)**Yichu Zhou, Vivek Srikumar
25. **[NPIs Aren't Exactly Easy: Variation in Licensing across Large Language Models ↗](https://aclanthology.org/2023.blackboxnlp-1.25/)**Deanna DeCarlo, William Palmer, Michael Wilson et al.

[See all 29 papers in BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2023 — accepted papers →](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2023/papers/)

## Papers with our summary in our library (2)

The most cited first (OpenAlex citations plus our library's).

1. [**When Your Language Model Cannot Even Do Determiners Right: Probing for Anti-Presuppositions and the Maximize Presupposition! Principle**Judith Sieker, Sina Zarrieß*2023 · 9 citations*](https://md.research.elamur.ai/free/en/papers/sieker-2023-when-your-language-model-cannot/)
2. **[On Quick Kisses and How to Make Them Count: A Study on Event Construal in Light Verb Constructions with BERT](https://md.research.elamur.ai/free/en/papers/liu-2023-quick-kisses-how-make-them/) [BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP](https://md.research.elamur.ai/free/en/venues/blackboxnlp/)**Chenxin Liu, Emmanuele Chersoni*2023 · 2 citations*

## Top topics

Topics of its works in our library, with the number of works on each.

[Implicature (1)](https://md.research.elamur.ai/free/en/topics/implicature/) · [Language models & pretraining (1)](https://md.research.elamur.ai/free/en/topics/language-models/) · [Interpretability (1)](https://md.research.elamur.ai/free/en/topics/interpretability/) · [Idioms & multiword expressions (1)](https://md.research.elamur.ai/free/en/topics/multiword-expressions/) · [English (1)](https://md.research.elamur.ai/free/en/topics/english/)

## Fields

[Arts and Humanities (2)](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science (1)](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Neuroscience (1)](https://md.research.elamur.ai/free/en/shelves/neuroscience/) · [Psychology (1)](https://md.research.elamur.ai/free/en/shelves/psychology/)

## Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

[🧑‍🔬**Judith Sieker**1 work here · 9 citations](https://md.research.elamur.ai/free/en/authors/judith-sieker/) · [🧑‍🔬**Sina Zarrieß**1 work here · 9 citations](https://md.research.elamur.ai/free/en/authors/sina-zarriess/) · [🧑‍🔬**Emmanuele Chersoni**1 work here · 2 citations](https://md.research.elamur.ai/free/en/authors/emmanuele-chersoni/)

## Top institutions

Institutions on the bylines of its works here, by the number of works.

[🎓**Hong Kong Polytechnic University** Hong Kong · China 1 work here](https://md.research.elamur.ai/free/en/universities/hong-kong-polytechnic-university/) · [🎓**Bielefeld University** Bielefeld · Germany 1 work here](https://md.research.elamur.ai/free/en/universities/bielefeld-university/)

Place and dates from the event's site or the ACL Anthology; works and citations from OpenAlex and our library.

- [← previous BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP 2022](https://md.research.elamur.ai/free/en/venues/blackboxnlp/2022/)
- [↑ back to BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP](https://md.research.elamur.ai/free/en/venues/blackboxnlp/)