Reshmi Ghosh
YOU?
Author Swipe
View article: SAGEval: The frontiers of Satisfactory Agent based NLG Evaluation for reference-free open-ended text
SAGEval: The frontiers of Satisfactory Agent based NLG Evaluation for reference-free open-ended text Open
Large Language Model (LLM) integrations into applications like Microsoft365 suite and Google Workspace for creating/processing documents, emails, presentations, etc. has led to considerable enhancements in productivity and time savings. Bu…
View article: Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis
Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis Open
Retrieval Augmented Generation (RAG) is a widely used approach for leveraging external context in several natural language applications such as question answering and information retrieval. Yet, the exact nature in which a Language Model (…
View article: From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries
From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries Open
Retrieval Augmented Generation (RAG) enriches the ability of language models to reason using external context to augment responses for a given user prompt. This approach has risen in popularity due to practical applications in various appl…
View article: Leveraging Language Models to Detect Greenwashing
Leveraging Language Models to Detect Greenwashing Open
In recent years, climate change repercussions have increasingly captured public interest. Consequently, corporations are emphasizing their environmental efforts in sustainability reports to bolster their public image. Yet, the absence of s…
View article: Topic Segmentation of Semi-Structured and Unstructured Conversational Datasets using Language Models
Topic Segmentation of Semi-Structured and Unstructured Conversational Datasets using Language Models Open
Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic segmentati…
View article: On Surgical Fine-tuning for Language Encoders
On Surgical Fine-tuning for Language Encoders Open
Fine-tuning all the layers of a pre-trained neural language encoder (either using all the parameters or using parameter-efficient methods) is often the de-facto way of adapting it to a new task. We show evidence that for different downstre…
View article: On Surgical Fine-tuning for Language Encoders
On Surgical Fine-tuning for Language Encoders Open
Abhilasha Lodha, Gayatri Belapurkar, Saloni Chalkapurkar, Yuanming Tao, Reshmi Ghosh, Samyadeep Basu, Dmitrii Petrov, Soundararajan Srinivasan. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.
View article: Topic Segmentation in the Wild: Towards Segmentation of Semi-structured & Unstructured Chats
Topic Segmentation in the Wild: Towards Segmentation of Semi-structured & Unstructured Chats Open
Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic segmentati…
View article: Reconstruction of Long-Term Historical Demand Data
Reconstruction of Long-Term Historical Demand Data Open
Long-term planning of a robust power system requires the understanding of changing demand patterns. Electricity demand is highly weather sensitive. Thus, the supply side variation from introducing intermittent renewable sources, juxtaposed…
View article: Clinico-pathological study of chronic nephropathy in a dog
Clinico-pathological study of chronic nephropathy in a dog Open
An ailing male dog was presented for treatment in the Teaching Veterinary Clinical Complex Anjora, Durg, Chhattisgarh with the history of vomiting, polyuria, hematuria and anorexia. The blood and urinalysis revealed elevated BUN and creati…
View article: Prevalence of Bovine Viral Diarrhoea virus in West Bengal, India.
Prevalence of Bovine Viral Diarrhoea virus in West Bengal, India. Open
Bovine Viral Diarrhea (BVD) is one of the most economically important diseases in cattle. The present study was undertaken to diagnose the persistently infected (PI) animals by AntigenELISA and Reverse Transcriptase PCR using serum samples…