2 citations · 6 across the 21 of their papers we have counts for
21 papers
The Effect of Quantization on Clinical Benchmarks: Accuracy and Safety Across Model Families
Leonard Twagirayezu, Prasenjit Mitra
Quantization enables deployment of large language models on resource-constrained clinical edge devices, but its effect on clinical accuracy and safety remains understudied. We eval…
Reasoning-Aware Compression: Identifying and Protecting Vulnerable Reasoning Circuits for Energy-Efficient LLM Deployment
Leonard Twagirayezu, Prasenjit Mitra
Large Reasoning Models (LRMs) impose substantial energy costs during deployment, yet current compression methods apply uniform quantization across all components, risking damage to…
From Speech to Text Corpora: Evaluating ASR-Based Data Acquisition for Low-Resource Fongbe and Hausa
Mahounan Pericles Adjovi, Victor Olufemi, Roald Eiselen +1
Low-resource African languages lack text corpora needed for language model training. We investigate whether ASR pipelines can extend text resources for two typologically distinct W…
Evaluating Large Language Models for Hausa and Fongbe Machine Translation: Benchmarks, Failures, and Metric Reliability
Mahounan Pericles Adjovi, Roald Eiselen, Prasenjit Mitra
We investigate the translation quality of current large language models (LLMs) for English-to-Hausa and English-to-Fongbe - two typologically distinct West African languages from t…
WaxalNet: Benchmarking and Adapting Speech Recognition for Spontaneous Speech in 19 African Languages
Victor Tolulope Olufemi, Oreoluwa Babatunde, Ramsey Njema +28
Multilingual speech foundation models claim broad language coverage, but how well they handle spontaneous African speech, and how best to adapt them, remains unclear. We benchmark…
HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation
Edward Ajayi, Prasenjit Mitra
Humor generation poses a significant challenge for Large Language Models (LLMs), because their standard training objective (next-token prediction) inherently conflicts with the sur…
When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP
Mahounan Pericles Adjovi, Roald Eiselen, Prasenjit Mitra
Data scarcity limits NLP development for low-resource African languages. We evaluate two data augmentation methods -- LLM-based generation (Gemini 2.5 Flash) and back-translation (…
Mining Large Language Models for Low-Resource Language Data: Comparing Elicitation Strategies for Hausa and Fongbe
Mahounan Pericles Adjovi, Roald Eiselen, Prasenjit Mitra
Large language models (LLMs) are trained on data contributed by low-resource language communities, yet the linguistic knowledge encoded in these models remains accessible only thro…
A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development
Mahounan Pericles Adjovi, Victor Olufemi, Roald Eiselen +1
This survey provides a comprehensive catalog of publicly available text and speech resources for two West African languages: Hausa, an Afroasiatic language with approximately 80-10…
HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models
Edward Ajayi, Prasenjit Mitra
Evaluating humor in large language models (LLMs) is an open challenge because existing approaches yield isolated, incomparable metrics rather than unified model rankings, making it…
Budget-Xfer: Budget-Constrained Source Language Selection for Cross-Lingual Transfer to African Languages
Tewodros Kederalah Idris, Roald Eiselen, Prasenjit Mitra
Cross-lingual transfer learning enables NLP for low-resource languages by leveraging labeled data from higher-resource sources, yet existing comparisons of source language selectio…
QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals
Nan Zhang, Eugene Kwek, Yusen Zhang +4
Weight-only quantization is important for compressing Large Language Models (LLMs). Inspired by the spirit of classical magnitude pruning, we study whether the magnitude of weight…
Can Embedding Similarity Predict Cross-Lingual Transfer? A Systematic Study on African Languages
Tewodros Kederalah Idris, Prasenjit Mitra, Roald Eiselen
Cross-lingual transfer is essential for building NLP systems for low-resource African languages, but practitioners lack reliable methods for selecting source languages. We systemat…
TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora
Priyanka Kargupta, Nan Zhang, Yunyi Zhang +3
The rapid evolution of scientific fields introduces challenges in organizing and retrieving scientific literature. While expert-curated taxonomies have traditionally addressed this…
When Reasoning Meets Compression: Understanding the Effects of LLMs Compression on Large Reasoning Models
Nan Zhang, Eugene Kwek, Yusen Zhang +3
Compression methods, including quantization, distillation, and pruning, improve the computational efficiency of large reasoning models (LRMs). However, existing studies either fail…
SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
Nan Zhang, Prafulla Kumar Choubey, Alexander Fabbri +5
Indexing is an important step towards strong performance in retrieval-augmented generation (RAG) systems. However, existing methods organize data based on either semantic similarit…
Pruning as a Domain-specific LLM Extractor
Nan Zhang, Yanchi Liu, Xujiang Zhao +5
Large Language Models (LLMs) have exhibited remarkable proficiency across a wide array of NLP tasks. However, the escalation in model size also engenders substantial deployment cos…
PEaCE: A Chemistry-Oriented Dataset for Optical Character Recognition on Scientific Documents
Nan Zhang, Connor Heaton, Sean Timothy Okonsky +2
Optical Character Recognition (OCR) is an established task with the objective of identifying the text present in an image. While many off-the-shelf OCR models exist, they are often…
Milestones in Bengali Sentiment Analysis leveraging Transformer-models: Fundamentals, Challenges and Future Directions
Saptarshi Sengupta, Shreya Ghosh, Prasenjit Mitra +1
Sentiment Analysis (SA) refers to the task of associating a view polarity (usually, positive, negative, or neutral; or even fine-grained such as slightly angry, sad, etc.) to a giv…
Towards Efficient Methods in Medical Question Answering using Knowledge Graph Embeddings
Saptarshi Sengupta, Connor Heaton, Suhan Cui +2
In Natural Language Processing (NLP), Machine Reading Comprehension (MRC) is the task of answering a question based on a given context. To handle questions in the medical domain, m…
TOP-Training: Target-Oriented Pretraining for Medical Extractive Question Answering
Saptarshi Sengupta, Connor Heaton, Shreya Ghosh +3
We study extractive question-answering in the medical domain (Medical-EQA). This problem has two main challenges: (i) domain specificity, as most AI models lack necessary domain kn…