Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023)

Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor 2023-07 Association for Computational Linguistics Toronto, Canada text conference publication trustnlp-2023-trustworthy https://aclanthology.org/2023.trustnlp-1.0/ Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training Dongfang Li author Baotian Hu author Qingcai Chen author Shan He author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication li-etal-2023-towards 10.18653/v1/2023.trustnlp-1.1 https://aclanthology.org/2023.trustnlp-1.1/ 2023-07 1 14 Driving Context into Text-to-Text Privatization Stefan Arnold author Dilara Yesilbas author Sven Weinzierl author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication arnold-etal-2023-driving 10.18653/v1/2023.trustnlp-1.2 https://aclanthology.org/2023.trustnlp-1.2/ 2023-07 15 25 Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models Pranav Narayanan Venkit author Mukund Srinath author Shomir Wilson author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication narayanan-venkit-etal-2023-automated 10.18653/v1/2023.trustnlp-1.3 https://aclanthology.org/2023.trustnlp-1.3/ 2023-07 26 34 Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script Xi Cao author Dolma Dawa author Nuo Qun author Trashi Nyima author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication cao-etal-2023-pay-attention 10.18653/v1/2023.trustnlp-1.4 https://aclanthology.org/2023.trustnlp-1.4/ 2023-07 35 46 Can we trust the evaluation on ChatGPT? Rachith Aiyappa author Jisun An author Haewoon Kwak author Yong-yeol Ahn author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication aiyappa-etal-2023-trust 10.18653/v1/2023.trustnlp-1.5 https://aclanthology.org/2023.trustnlp-1.5/ 2023-07 47 54 Improving Factuality of Abstractive Summarization via Contrastive Reward Learning I-chun Chern author Zhiruo Wang author Sanjan Das author Bhavuk Sharma author Pengfei Liu author Graham Neubig author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication chern-etal-2023-improving 10.18653/v1/2023.trustnlp-1.6 https://aclanthology.org/2023.trustnlp-1.6/ 2023-07 55 60 Examining the Causal Impact of First Names on Language Models: The Case of Social Commonsense Reasoning Sullam Jeoung author Jana Diesner author Halil Kilicoglu author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication jeoung-etal-2023-examining 10.18653/v1/2023.trustnlp-1.7 https://aclanthology.org/2023.trustnlp-1.7/ 2023-07 61 72 Reliability Check: An Analysis of GPT-3’s Response to Sensitive Topics and Prompt Wording Aisha Khatun author Daniel Brown author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication khatun-brown-2023-reliability 10.18653/v1/2023.trustnlp-1.8 https://aclanthology.org/2023.trustnlp-1.8/ 2023-07 73 95 Sample Attackability in Natural Language Adversarial Attacks Vyas Raina author Mark Gales author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication raina-gales-2023-sample 10.18653/v1/2023.trustnlp-1.9 https://aclanthology.org/2023.trustnlp-1.9/ 2023-07 96 107 A Keyword Based Approach to Understanding the Overpenalization of Marginalized Groups by English Marginal Abuse Models on Twitter Kyra Yee author Alice Schoenauer Sebag author Olivia Redfield author Matthias Eck author Emily Sheng author Luca Belli author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication yee-etal-2023-keyword 10.18653/v1/2023.trustnlp-1.10 https://aclanthology.org/2023.trustnlp-1.10/ 2023-07 108 120 An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models Saghar Hosseini author Hamid Palangi author Ahmed Hassan Awadallah author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication hosseini-etal-2023-empirical 10.18653/v1/2023.trustnlp-1.11 https://aclanthology.org/2023.trustnlp-1.11/ 2023-07 121 134 Linguistic Properties of Truthful Response Bruce W Lee author Benedict Florance Arockiaraj author Helen Jin author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication lee-etal-2023-linguistic 10.18653/v1/2023.trustnlp-1.12 https://aclanthology.org/2023.trustnlp-1.12/ 2023-07 135 140 Debunking Biases in Attention Shijing Chen author Usman Naseem author Imran Razzak author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication chen-etal-2023-debunking 10.18653/v1/2023.trustnlp-1.13 https://aclanthology.org/2023.trustnlp-1.13/ 2023-07 141 150 Guiding Text-to-Text Privatization by Syntax Stefan Arnold author Dilara Yesilbas author Sven Weinzierl author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication arnold-etal-2023-guiding 10.18653/v1/2023.trustnlp-1.14 https://aclanthology.org/2023.trustnlp-1.14/ 2023-07 151 162 Are fairness metric scores enough to assess discrimination biases in machine learning? Fanny Jourdan author Laurent Risser author Jean-michel Loubes author Nicholas Asher author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication jourdan-etal-2023-fairness 10.18653/v1/2023.trustnlp-1.15 https://aclanthology.org/2023.trustnlp-1.15/ 2023-07 163 174 DEPTH+: An Enhanced Depth Metric for Wikipedia Corpora Quality Saied Alshahrani author Norah Alshahrani author Jeanna Matthews author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication alshahrani-etal-2023-depth 10.18653/v1/2023.trustnlp-1.16 https://aclanthology.org/2023.trustnlp-1.16/ 2023-07 175 189 Distinguishing Fact from Fiction: A Benchmark Dataset for Identifying Machine-Generated Scientific Papers in the LLM Era. Edoardo Mosca author Mohamed Hesham Ibrahim Abdalla author Paolo Basso author Margherita Musumeci author Georg Groh author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication mosca-etal-2023-distinguishing 10.18653/v1/2023.trustnlp-1.17 https://aclanthology.org/2023.trustnlp-1.17/ 2023-07 190 207 Detecting Personal Information in Training Corpora: an Analysis Nishant Subramani author Sasha Luccioni author Jesse Dodge author Margaret Mitchell author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication subramani-etal-2023-detecting 10.18653/v1/2023.trustnlp-1.18 https://aclanthology.org/2023.trustnlp-1.18/ 2023-07 208 220 Enhancing textual counterfactual explanation intelligibility through Counterfactual Feature Importance Milan Bhan author Jean-noel Vittaut author Nicolas Chesneau author Marie-jeanne Lesot author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication bhan-etal-2023-enhancing 10.18653/v1/2023.trustnlp-1.19 https://aclanthology.org/2023.trustnlp-1.19/ 2023-07 221 231 Privacy- and Utility-Preserving NLP with Anonymized data: A case study of Pseudonymization Oleksandr Yermilov author Vipul Raheja author Artem Chernodub author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication yermilov-etal-2023-privacy 10.18653/v1/2023.trustnlp-1.20 https://aclanthology.org/2023.trustnlp-1.20/ 2023-07 232 241 GPTs Don’t Keep Secrets: Searching for Backdoor Watermark Triggers in Autoregressive Language Models Evan Lucas author Timothy Havens author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication lucas-havens-2023-gpts 10.18653/v1/2023.trustnlp-1.21 https://aclanthology.org/2023.trustnlp-1.21/ 2023-07 242 248 Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data Xinzhe Li author Ming Liu author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication li-liu-2023-make 10.18653/v1/2023.trustnlp-1.22 https://aclanthology.org/2023.trustnlp-1.22/ 2023-07 249 259 Training Data Extraction From Pre-trained Language Models: A Survey Shotaro Ishihara author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication ishihara-2023-training 10.18653/v1/2023.trustnlp-1.23 https://aclanthology.org/2023.trustnlp-1.23/ 2023-07 260 275 Expanding Scope: Adapting English Adversarial Attacks to Chinese Hanyu Liu author Chengyuan Cai author Yanjun Qi author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication liu-etal-2023-expanding 10.18653/v1/2023.trustnlp-1.24 https://aclanthology.org/2023.trustnlp-1.24/ 2023-07 276 286 IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks Xuanli He author Jun Wang author Benjamin Rubinstein author Trevor Cohn author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication he-etal-2023-imbert 10.18653/v1/2023.trustnlp-1.25 https://aclanthology.org/2023.trustnlp-1.25/ 2023-07 287 301 On The Real-world Performance of Machine Translation: Exploring Social Media Post-authors’ Perspectives Ananya Gupta author Jae Takeuchi author Bart Knijnenburg author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication gupta-etal-2023-real 10.18653/v1/2023.trustnlp-1.26 https://aclanthology.org/2023.trustnlp-1.26/ 2023-07 302 310 Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values Yejin Bang author Tiezheng Yu author Andrea Madotto author Zhaojiang Lin author Mona Diab author Pascale Fung author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication bang-etal-2023-enabling 10.18653/v1/2023.trustnlp-1.27 https://aclanthology.org/2023.trustnlp-1.27/ 2023-07 311 325 Strength in Numbers: Estimating Confidence of Large Language Models by Prompt Agreement Gwenyth Portillo Wightman author Alexandra Delucia author Mark Dredze author 2023-07 text Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) Anaelia Ovalle editor Kai-Wei Chang editor Ninareh Mehrabi editor Yada Pruksachatkun editor Aram Galystan editor Jwala Dhamala editor Apurv Verma editor Trista Cao editor Anoop Kumar editor Rahul Gupta editor Association for Computational Linguistics Toronto, Canada conference publication portillo-wightman-etal-2023-strength 10.18653/v1/2023.trustnlp-1.28 https://aclanthology.org/2023.trustnlp-1.28/ 2023-07 326 362