Papers by Maunendra Sankar Desarkar
DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation metrics for cultural awareness and alignment are lacking . Existing datasets for culture specific items (CSIs) focus primarily on concepts at the regional level and may contain false positives. |
| Approach: | They propose a new CSI dataset for Indian culture that measures cultural competence . they use a CSI created by LLM as Judge and human evaluations from diverse regions . |
| Outcome: | The proposed model shows that it is capable of generating culturally relevant adaptations across multiple cultural facets. |
Multilingual Tokenization through the Lens of Indian Languages: Challenges and Insights (2026.findings-acl)
Copied to clipboard
Maharaj Brahma, N J Karthika, Rajat Verma, Nagasai Saketh Naidu, Rohit Saluja, Maunendra Sankar Desarkar, Ganesh Ramakrishnan
| Challenge: | Existing tokenizers are often skewed towards high-resource languages limiting their effectiveness for linguistically diverse and morphologically rich languages. |
| Approach: | They evaluate multilingual tokenization across 17 Indic languages spanning 11 scripts and two language families. |
| Outcome: | The proposed method improves tokenization quality and vocabulary size in 17 languages . poor tokenization can lead to increase in sequence lengths, fragment meaningful units, weaken model's ability to capture linguistic structure and semantics. |
DivHSK: Diverse Headline Generation using Self-Attention based Keyword Selection (2023.findings-acl)
Copied to clipboard
| Challenge: | Diverse headline generation is an NLP task where the goal is to generate multiple headlines that are true to the content of the article but are different among themselves. |
| Approach: | They propose a novel model that generates multiple diverse headlines by using a pre-trained encoder and a cluster-specific keyword set. |
| Outcome: | The proposed model outperforms existing literature and their strong baselines and emerges as a state-of-the-art model. |
A Unified View on Emotion Representation in Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Recent studies show the presence of emotion concepts in the hidden state representations, but it’s unclear if the model has a robust representation consistent across different datasets. |
| Approach: | They propose a unified view to understand emotion representation in Large Language Models by experimenting with diverse datasets and prompts. |
| Outcome: | The proposed model can be interchanged between datasets with minimal impact on performance. |
Semantics-aware prompting for translating NOtices To AirMen (2025.findings-acl)
Copied to clipboard
| Challenge: | A NOTAM or NOtice To AirMen is a crucial notification for different stakeholders . writing and understanding these messages puts heavy cognitive load on its end users. |
| Approach: | They propose a framework to translate NOTAMs into English natural language using LLMs . they use context-aware semantic prompting techniques paired with domain-specific rules . |
| Outcome: | The proposed approach improves translation accuracy and clarity using semantic prompting techniques . the proposed framework was evaluated using LLMs of varying sizes and 8 evaluation metrics . |
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in NLP focus on large annotated training data. |
| Approach: | They propose an unsupervised framework that does not use parallel or pseudo-parallel/back-translated data. |
| Outcome: | The proposed framework does not use parallel or pseudo-parallel/back-translated data. |