📰 Workshop on Trustworthy NLP 2023 — accepted papers

Workshop on Trustworthy NLP 2023 is the 2023 edition of the Workshop on Trustworthy NLP, held in Toronto, Canada, July 2023 (publisher: Association for Computational Linguistics). The ACL Anthology lists 28 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.

📍 Toronto, Canada · 🗓 July 2023

Most cited papers

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

1. Can we trust the evaluation on ChatGPT?Rachith Aiyappa, Jisun An, Haewoon Kwak et al.68 citations · our summary
2. Privacy- and Utility-Preserving NLP with Anonymized data: A case study of Pseudonymization ↗Oleksandr Yermilov, Vipul Raheja, Artem Chernodub30 citations
3. Detecting Personal Information in Training Corpora: an Analysis ↗Nishant Subramani, Sasha Luccioni, Jesse Dodge et al.20 citations
4. Training Data Extraction From Pre-trained Language Models: A Survey ↗Shotaro Ishihara19 citations
5. Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models ↗Pranav Narayanan Venkit, Mukund Srinath, Shomir Wilson15 citations
6. Distinguishing Fact from Fiction: A Benchmark Dataset for Identifying Machine-Generated Scientific Papers in the LLM Era. ↗Edoardo Mosca, Mohamed Hesham Ibrahim Abdalla, Paolo Basso et al.14 citations
7. Improving Factuality of Abstractive Summarization via Contrastive Reward Learning ↗I-chun Chern, Zhiruo Wang, Sanjan Das et al.11 citations
8. Strength in Numbers: Estimating Confidence of Large Language Models by Prompt Agreement ↗Gwenyth Portillo Wightman, Alexandra Delucia, Mark Dredze10 citations
9. Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording ↗Aisha Khatun, Daniel Brown9 citations
10. GPTs Don't Keep Secrets: Searching for Backdoor Watermark Triggers in Autoregressive Language Models ↗Evan Lucas, Timothy Havens7 citations

All accepted papers (28)

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

1. Can we trust the evaluation on ChatGPT?Rachith Aiyappa, Jisun An, Haewoon Kwak et al.68 citations · our summary
2. Privacy- and Utility-Preserving NLP with Anonymized data: A case study of Pseudonymization ↗Oleksandr Yermilov, Vipul Raheja, Artem Chernodub30 citations
3. Detecting Personal Information in Training Corpora: an Analysis ↗Nishant Subramani, Sasha Luccioni, Jesse Dodge et al.20 citations
4. Training Data Extraction From Pre-trained Language Models: A Survey ↗Shotaro Ishihara19 citations
5. Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models ↗Pranav Narayanan Venkit, Mukund Srinath, Shomir Wilson15 citations
6. Distinguishing Fact from Fiction: A Benchmark Dataset for Identifying Machine-Generated Scientific Papers in the LLM Era. ↗Edoardo Mosca, Mohamed Hesham Ibrahim Abdalla, Paolo Basso et al.14 citations
7. Improving Factuality of Abstractive Summarization via Contrastive Reward Learning ↗I-chun Chern, Zhiruo Wang, Sanjan Das et al.11 citations
8. Strength in Numbers: Estimating Confidence of Large Language Models by Prompt Agreement ↗Gwenyth Portillo Wightman, Alexandra Delucia, Mark Dredze10 citations
9. Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording ↗Aisha Khatun, Daniel Brown9 citations
10. GPTs Don't Keep Secrets: Searching for Backdoor Watermark Triggers in Autoregressive Language Models ↗Evan Lucas, Timothy Havens7 citations
11. Guiding Text-to-Text Privatization by Syntax ↗Stefan Arnold, Dilara Yesilbas, Sven Weinzierl6 citations
12. IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks ↗Xuanli He, Jun Wang, Benjamin Rubinstein et al.6 citations
13. Expanding Scope: Adapting English Adversarial Attacks to Chinese ↗Hanyu Liu, Chengyuan Cai, Yanjun Qi5 citations
14. Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script ↗Xi Cao, Dolma Dawa, Nuo Qun et al.5 citations
15. A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on TwitterKyra Yee, Alice Schoenauer Sebag, Olivia Redfield et al.4 citations · our summary
16. Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training ↗Dongfang Li, Baotian Hu, Qingcai Chen et al.4 citations
17. An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language ModelsSaghar Hosseini, Hamid Palangi, Ahmed Hassan Awadallah3 citations · our summary
18. DEPTH+: An Enhanced Depth Metric for Wikipedia Corpora Quality ↗Saied Alshahrani, Norah Alshahrani, Jeanna Matthews3 citations
19. Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data ↗Xinzhe Li, Ming Liu3 citations
20. Driving Context into Text-to-Text Privatization ↗Stefan Arnold, Dilara Yesilbas, Sven Weinzierl2 citations
21. Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values ↗Yejin Bang, Tiezheng Yu, Andrea Madotto et al.2 citations
22. Enhancing textual counterfactual explanation intelligibility through Counterfactual Feature Importance ↗Milan Bhan, Jean-noel Vittaut, Nicolas Chesneau et al.2 citations
23. On The Real-world Performance of Machine Translation: Exploring Social Media Post-authors' Perspectives ↗Ananya Gupta, Jae Takeuchi, Bart Knijnenburg2 citations
24. Are fairness metric scores enough to assess discrimination biases in machine learning? ↗Fanny Jourdan, Laurent Risser, Jean-michel Loubes et al.1 citation
25. Debunking Biases in Attention ↗Shijing Chen, Usman Naseem, Imran Razzak1 citation

See all 28 papers in Workshop on Trustworthy NLP 2023 — accepted papers →

📄 Papers with our summary in our library (2)

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

1. Can we trust the evaluation on ChatGPT?Workshop on Trustworthy NLPRachith Aiyappa, Jisun An, Haewoon Kwak, et al.2023 · 103 citations
2. A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on TwitterWorkshop on Trustworthy NLPKyra Yee, Alice Schoenauer Sebag, Olivia Redfield, et al.2023 · 4 citations

🧭 Top topics

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

📏Evaluation & benchmarks (1)English (1)

📚 Fields

🖥️Computer Science (2)🤝Social Sciences (2)🎭Arts and Humanities (1)

🧑‍🔬 Top authors

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

🏛️ Top institutions

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

🎓Indiana University BloomingtonBloomington · United States1 work here🎓Indiana UniversityBloomington · United States1 work here

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

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/venues/trustnlp/2023/