Papers by Priyanka Kargupta
TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora (2025.acl-long)
Copied to clipboard
| Challenge: | Recent automated taxonomies over-rely on a specific corpus, sacrificing generalizability, or depend heavily on the general knowledge of large language models (LLMs) . |
| Approach: | They propose a framework that dynamically adapts an LLM-generated taxonomy to a given corpus across multiple dimensions. |
| Outcome: | The proposed framework performs iterative hierarchical classification, expanding both the taxonomy width and depth based on corpus’ topical distribution. |
Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis (2025.acl-long)
Copied to clipboard
| Challenge: | Existing comparative summarization methods focus on surface-level semantic differences, which may not capture the most relevant distinctions. |
| Approach: | They propose a framework which transforms scientific papers into LLM personas that debate their respective novelties. |
| Outcome: | The proposed framework generates informative arguments and effectively contrasts papers, and supports researchers in their literature review. |
Reaction Miner: An Integrated System for Chemical Reaction Extraction from Textual Data (2023.emnlp-demo)
Copied to clipboard
Ming Zhong, Siru Ouyang, Yizhu Jiao, Priyanka Kargupta, Leo Luo, Yanzhen Shen, Bobby Zhou, Xianrui Zhong, Xuan Liu, Hongxiang Li, Jinfeng Xiao, Minhao Jiang, Vivian Hu, Xuan Wang, Heng Ji, Martin Burke, Huimin Zhao, Jiawei Han
| Challenge: | Reaction Miner is a system designed to extract chemical reactions from raw scientific PDFs. |
| Approach: | They propose a system that extracts chemical reactions directly from raw scientific PDFs. |
| Outcome: | The proposed system can extract chemical reactions from raw scientific PDFs. |
Grounding Agent Memory in Contextual Intent (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models are deployed in long-horizon tasks that require agents to track interleaved goals, resolve references to prior information, and coordinate actions over extended trajectories. |
| Approach: | They propose an agentic memory system that indexes each trajectory step with a structured retrieval cue, contextual intent, and retrieves history by matching the current step’s intent. |
| Outcome: | The proposed system outperforms the strongest benchmark by 35.6%, with the largest gains as trajectory length increases. |
Beyond True or False: Retrieval-Augmented Hierarchical Analysis of Nuanced Claims (2025.acl-long)
Copied to clipboard
| Challenge: | Claims are often nuanced and cannot be clearly labeled as “true” or “false” . however, a claim can be dissected into integral aspects and sub-aspects that are individually easier to validate . |
| Approach: | They propose a retrieval-augmented generation-based framework for deconstructing nuanced claims . claim can be dissected into integral aspects and sub-aspects, which are easier to validate . |
| Outcome: | The proposed framework can be easily deconstructed into integral aspects and sub-aspects, which are easier to validate. |
Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code Debugging (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current large language models often give away solutions directly, making them ineffective instructors. |
| Approach: | They propose to use a state space-based planning algorithm to build a question tree based on a student's knowledge state to help students independently identify and resolve errors. |
| Outcome: | The proposed model is able to debug code efficiently with minimal turns and highly Socratic questioning. |
Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events (2025.acl-long)
Copied to clipboard
| Challenge: | State-of-the-art automatic event detection struggles with interpretability and adaptability to evolving large-scale key events. |
| Approach: | They propose a task which identifies episodes within a news corpus of key event articles. |
| Outcome: | The proposed framework achieves 59.2% gain across all metrics compared to baselines. |
MEGClass: Extremely Weakly Supervised Text Classification via Mutually-Enhancing Text Granularities (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for text classification use human annotations or a set of class seed words for supervision, which can be costly, especially in emerging domains. |
| Approach: | They propose a weakly-supervised method that leverages mutually-enhancing text granularities to learn a contextualized document representation that captures the most discriminative class indicators. |
| Outcome: | Extensive experiments on seven benchmark datasets show that MEGClass outperforms other weakly and extremely weakly supervised methods. |
NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment (2026.eacl-long)
Copied to clipboard
Antonia Karamolegkou, Angana Borah, Eunjung Cho, Sagnik Ray Choudhury, Martina Galletti, Pranav Gupta, Oana Ignat, Priyanka Kargupta, Neema Kotonya, Hemank Lamba, Sun-Joo Lee, Arushi Mangla, Ishani Mondal, Fatima Zahra Moudakir, Deniz Nazar, Poli Nemkova, Dina Pisarevskaya, Naquee Rizwan, Nazanin Sabri, Keenan Samway, Dominik Stammbach, Anna Steinberg Schulten, David Tomás, Steven R Wilson, Bowen Yi, Jessica H Zhu, Arkaitz Zubiaga, Anders Søgaard, Alexander Fraser, Zhijing Jin, Rada Mihalcea, Joel R. Tetreault, Daryna Dementieva
| Challenge: | This paper surveys work in "NLP for Social Good" across nine domains relevant to global development and risk agendas. |
| Approach: | This paper analyzes work in "NLP for Social Good" across nine domains relevant to global development and risk agendas. |
| Outcome: | The paper analyzes work in "NLP for Social Good" across nine domains relevant to global development and risk agendas. |