Papers by Bishwaranjan Bhattacharjee
Muted: Multilingual Targeted Offensive Speech Identification and Visualization (2023.emnlp-demo)
Copied to clipboard
Christoph Tillmann, Aashka Trivedi, Sara Rosenthal, Santosh Borse, Rong Zhang, Avirup Sil, Bishwaranjan Bhattacharjee
| Challenge: | Existing visualizations of offensive language use only sentence level annotations, but there are few that explore spans and other languages. |
| Approach: | They propose a system to identify multilingual HAP content by displaying offensive arguments and their targets using heat maps to indicate their intensity. |
| Outcome: | The proposed model can identify toxic spans without further fine-tuning using existing models and its attention mechanism out-of-the-box. |
Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models acquire general knowledge from pretraining but pretraining data contain undesirable social biases which can be perpetuated or even amplified by LLMs. |
| Approach: | They propose an efficient yet effective annotation pipeline to investigate social biases in pretraining data. |
| Outcome: | The proposed pipeline investigates social biases in the pretraining corpus using protected attribute detection and regard classification. |
A Simple-Yet-Efficient Instruction Augmentation Method for Zero-Shot Sentiment Classification (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies have used labeled sentiment instances to instruction tune LLMs, improving zero-shot sentiment classification performance. |
| Approach: | They propose a simple-yet-efficient method which does not rely on actual labeled sentiment instances. |
| Outcome: | The proposed method outperforms LLMs tuned with more complex instruction tuning methods by 5.1 points and increases scores by 30 points. |
A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Large language models are often inefficient for real-world deployment due to expensive inference costs. |
| Approach: | They propose to use knowledge distillation to transfer the knowledge of the original model to a smaller, more efficient student model. |
| Outcome: | The proposed method is the best for multi-lingual and multilingual student architectures. |
INDUS: Effective and Efficient Language Models for Scientific Applications (2024.emnlp-industry)
Copied to clipboard
Bishwaranjan Bhattacharjee, Aashka Trivedi, Masayasu Muraoka, Muthukumaran Ramasubramanian, Takuma Udagawa, Iksha Gurung, Nishan Pantha, Rong Zhang, Bharath Dandala, Rahul Ramachandran, Manil Maskey, Kaylin Bugbee, Michael Little, Elizabeth Fancher, Irina Gerasimov, Armin Mehrabian, Lauren Sanders, Sylvain Costes, Sergi Blanco-Cuaresma, Kelly Lockhart, Thomas Allen, Felix Grezes, Megan Ansdell, Alberto Accomazzi, Yousef El-Kurdi, Davis Wertheimer, Birgit Pfitzmann, Cesar Berrospi Ramis, Michele Dolfi, Rafael Lima, Panagiotis Vagenas, S. Mukkavilli, Peter Staar, Sanaz Vahidinia, Ryan McGranaghan, Tsengdar Lee
| Challenge: | Large language models trained on general domain corpora showed remarkable results on natural language processing tasks. |
| Approach: | They develop a suite of large language models trained on general domain corpora that address NLP tasks and smaller versions of them created using knowledge distillation. |
| Outcome: | The proposed models outperform general-purpose and domain-specific encoders on new and existing tasks and in industrial settings. |
Visual Objects As Context: Exploiting Visual Objects for Lexical Entailment (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing word representation methods for lexical entailment have been shown to hold on text, but they have not been tested on visual objects. |
| Approach: | They propose a word representation method derived from visual objects in associated images to tackle the lexical entailment task. |
| Outcome: | The proposed method outperforms existing unsupervised representation methods. |
A Simple Yet Strong Domain-Agnostic De-bias Method for Zero-Shot Sentiment Classification (2023.findings-acl)
Copied to clipboard
| Challenge: | a recent study shows that large language models are biased to their pre-training data, leading to poor performance in prompt templates. |
| Approach: | They propose a domain-agnostic data construction method to de-bias a given prompt template . they show that domain-based generic responses are superior to in-domain ground-truth data . |
| Outcome: | The proposed method improves sentiment analysis tasks across domains and domains . it also yields better performance than existing in-domain models . |