Papers by Sukannya Purkayastha

7 papers
Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning (2023.emnlp-demo)

Copied to clipboard

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations