Papers by Sukannya Purkayastha
Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning (2023.emnlp-demo)
Copied to clipboard
Clifton Poth, Hannah Sterz, Indraneil Paul, Sukannya Purkayastha, Leon Engländer, Timo Imhof, Ivan Vulić, Sebastian Ruder, Iryna Gurevych, Jonas Pfeiffer
| Challenge: | Adapters is an open-source library that unifies parameter-efficient and modular transfer learning in large language models. |
| Approach: | They propose to integrate 10 different methods into a unified interface for parameter-efficient and modular transfer learning in large language models. |
| Outcome: | The proposed library is able to perform on multiple NLP tasks and is open-source. |
LazyReview: A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models struggle to detect lazy thinking in a zero-shot setting, but instruction-based fine-tuning significantly boosts performance by 10-20 performance points. |
| Approach: | They propose to use LazyReview to train junior reviewers in the community to detect lazy thinking in peer-review sentences annotated with fine-grained lazy thinking categories. |
| Outcome: | The proposed dataset shows that LLMs struggle to detect lazy thinking instances in a zero-shot setting, while instruction-based fine-tuning significantly boosts performance by 10-20 performance points. |
A Framework to Generate High-Quality Datapoints for Multiple Novel Intent Detection (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to detect novel intents have been tested in the last decade. |
| Approach: | They propose a framework to detect multiple novel intents with budgeted human annotation cost. |
| Outcome: | The proposed framework outperforms baseline methods in terms of accuracy and F1-score on a set of benchmark datasets. |
Exploring Jiu-Jitsu Argumentation for Writing Peer Review Rebuttals (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent work suggests that instead of directly countering surface-level reasoning, one should follow an argumentation style inspired by the Jiu-Jitsu “soft” combat system. |
| Approach: | They propose a task of attitude and theme-guided rebuttal generation for peer reviews to enrich existing discourse structure with attitude roots, attitude themes, and canonical reversals. |
| Outcome: | The proposed task is based on an existing dataset for discourse structure in peer reviews with attitude roots, attitude themes, and canonical rebuttals. |
Decision-Making with Deliberation: Meta-reviewing as a Document-grounded Dialogue (2026.eacl-long)
Copied to clipboard
| Challenge: | Prior research on meta-reviewing has treated this as a summarization problem over review reports . prior research demonstrated that decision-makers can be effectively assisted in such scenarios via dialogue agents. |
| Approach: | They propose to use large-scale large-language models to generate synthetic data for meta-reviewing . they then use these data to train dialogue agents tailored for meta review . |
| Outcome: | The proposed method outperforms *off-the-shelf* dialogue agents in meta-reviewing scenarios. |
Romanization-based Large-scale Adaptation of Multilingual Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large multilingual pretrained language models are limited by their vocabulary size and parameter budget. |
| Approach: | They explore the potential of leveraging transliteration on a massive scale to improve performance for multilingual pretrained language models. |
| Outcome: | The proposed transliteration tool outperforms other methods on low-resource languages. |
CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation (2025.findings-emnlp)
Copied to clipboard
Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan, Kareem Elzeky, Henok Biadglign Ademtew, Alham Fikri Aji, Vladimir Araujo, Israel Abebe Azime, Jinheon Baek, Frederico Belcavello, Fermin Cristobal, Jan Christian Blaise Cruz, Mary Dabre, Raj Dabre, Toqeer Ehsan, Naome A Etori, Fauzan Farooqui, Jiahui Geng, Guido Ivetta, Thanmay Jayakumar, Soyeong Jeong, Zheng Wei Lim, Aishik Mandal, Sofía Martinelli, Mihail Minkov Mihaylov, Daniil Orel, Aniket Pramanick, Sukannya Purkayastha, Israfel Salazar, Haiyue Song, Tiago Timponi Torrent, Debela Desalegn Yadeta, Injy Hamed, Atnafu Lambebo Tonja, Thamar Solorio
| Challenge: | a human-curated benchmark of over 5,800 triples of images is used to evaluate multimodal translation systems. |
| Approach: | They introduce a human-curated benchmark of over 5,800 triples of images along with parallel captions in English and regional languages. |
| Outcome: | The results show that visual context improves translation quality in culturally-specific items . |