Papers by Ashima Suvarna
ModelCitizens: Representing Community Voices in Online Safety (2025.emnlp-main)
Copied to clipboard
Ashima Suvarna, Christina A Chance, Karolina Naranjo, Hamid Palangi, Sophie Hao, Thomas Hartvigsen, Saadia Gabriel
| Challenge: | Existing toxic language detection models are trained on annotations that collapse diverse perspectives into a single ground truth. |
| Approach: | They propose to augment social media posts with conversational scenarios to reflect the impact of conversational context on toxicity. |
| Outcome: | The proposed model outperforms existing models on social media with conversational scenarios. |
#NotAWhore! A Computational Linguistic Perspective of Rape Culture and Victimization on Social Media (2020.acl-srw)
Copied to clipboard
| Challenge: | Recent surge in online forums and movements supporting sexual assault survivors has led to the emergence of a ‘virtual bubble’ where survivors can recount their stories. |
| Approach: | They propose a transfer-learning based method to identify victim blaming language on Twitter and a single step transfer-based classification method to classify it. |
| Outcome: | The proposed method is compared with various deep learning and machine learning models on a manually annotated domain-specific dataset. |
QUDSELECT: Selective Decoding for Questions Under Discussion Parsing (2024.emnlp-main)
Copied to clipboard
| Challenge: | Question Under Discussion (QUD) uses implicit questions to reveal discourse relationships between sentences. |
| Approach: | They propose a framework that selectively decodes the QUD dependency structures considering the QUC criteria. |
| Outcome: | The proposed framework outperforms the state-of-the-art baseline models by 9% in human evaluation and 4% in automatic evaluation. |
Evaluating the Impact of Sub-word Information and Cross-lingual Word Embeddings on Mi’kmaq Language Modelling (2020.lrec-1)
Copied to clipboard
| Challenge: | Mi'kmaq is an Indigenous language spoken primarily in Eastern Canada. |
| Approach: | They consider n-gram and RNN language models for Mi'kmaq and use them to investigate their performance. |
| Outcome: | The proposed model performs better than word-level models, but does not improve over word-based models. |
Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that acquiring human preferences by comparing generations is not effective for large language models. |
| Approach: | They propose a preference optimization objective that elicits preferences jointly over the instruction-response pairs. |
| Outcome: | The proposed approach outperforms prior preference optimizations by 5.2% and 3.3% in summarization and open-ended dialogue datasets. |
Improving Event Definition Following For Zero-Shot Event Detection (2024.acl-long)
Copied to clipboard
Zefan Cai, Po-Nien Kung, Ashima Suvarna, Mingyu Ma, Hritik Bansal, Baobao Chang, P. Jeffrey Brantingham, Wei Wang, Nanyun Peng
| Challenge: | Existing approaches on zero-shot event detection train models on datasets annotated with known event types and prompt them with unseen event definitions. |
| Approach: | They propose to train models to better follow event definitions by using an automatic generated Diverse Event Definition dataset. |
| Outcome: | The proposed model outperforms existing models on three open benchmarks on zero-shot event detection. |