activity
20242026
collaborators

5 papers

cs.LG2026

Benchmarking the Energy Savings with Speculative Decoding Strategies

Rohit Dutta, Paramita Koley, Soham Poddar +5

Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requ…

cs.CL2025

Utilising Large Language Models for Generating Effective Counter Arguments to Anti-Vaccine Tweets

Utsav Dhanuka, Soham Poddar, Saptarshi Ghosh

In an era where public health is increasingly influenced by information shared on social media, combatting vaccine skepticism and misinformation has become a critical societal goal…

cs.CL2025

Brevity is the soul of sustainability: Characterizing LLM response lengths

Soham Poddar, Paramita Koley, Janardan Misra +4

A significant portion of the energy consumed by Large Language Models (LLMs) arises from their inference processes; hence developing energy-efficient methods for inference is cruci…

cs.CL2025

Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models

Soham Poddar, Paramita Koley, Janardan Misra +3

Large language models (LLMs) are increasingly recognized for their exceptional generative capabilities and versatility across various tasks. However, the high inference costs assoc…

cs.CL2024

ICPR 2024 Competition on Multilingual Claim-Span Identification

Soham Poddar, Biswajit Paul, Moumita Basu +1

A lot of claims are made in social media posts, which may contain misinformation or fake news. Hence, it is crucial to identify claims as a first step towards claim verification. G…