Search Results - "Furniturewala, Shaz"

Turn-Level Empathy Prediction Using Psychological Indicators by Furniturewala, Shaz, Jaidka, Kokil

“…For the WASSA 2024 Empathy and Personality Prediction Shared Task, we propose a novel turn-level empathy detection method that decomposes empathy into six…”
Get full text

Impact of Decoding Methods on Human Alignment of Conversational LLMs by Furniturewala, Shaz, Jaidka, Kokil, Sharma, Yashvardhan

“…To be included into chatbot systems, Large language models (LLMs) must be aligned with human conversational conventions. However, being trained mainly on…”
Get full text

Beyond Text: Leveraging Multi-Task Learning and Cognitive Appraisal Theory for Post-Purchase Intention Analysis by Yeo, Gerard Christopher, Furniturewala, Shaz, Jaidka, Kokil

“…Supervised machine-learning models for predicting user behavior offer a challenging classification problem with lower average prediction performance scores…”
Get full text

Rhetorical Role Labeling of Legal Documents using Transformers and Graph Neural Networks by Gupta, Anshika, Furniturewala, Shaz, Kumari, Vijay, Sharma, Yashvardhan

“…A legal document is usually long and dense requiring human effort to parse it. It also contains significant amounts of jargon which make deriving insights from…”
Get full text

Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models by Furniturewala, Shaz, Jandial, Surgan, Java, Abhinav, Banerjee, Pragyan, Shahid, Simra, Bhatia, Sumit, Jaidka, Kokil

“…Existing debiasing techniques are typically training-based or require access to the model's internals and output distributions, so they are inaccessible to…”
Get full text

All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation by Banerjee, Pragyan, Java, Abhinav, Jandial, Surgan, Shahid, Simra, Furniturewala, Shaz, Krishnamurthy, Balaji, Bhatia, Sumit

“…Fairness in Language Models (LMs) remains a longstanding challenge, given the inherent biases in training data that can be perpetuated by models and affect the…”
Get full text

BITS Pilani at HinglishEval: Quality Evaluation for Code-Mixed Hinglish Text Using Transformers by Furniturewala, Shaz, Kumari, Vijay, Dash, Amulya Ratna, Kedia, Hriday, Sharma, Yashvardhan

“…Code-Mixed text data consists of sentences having words or phrases from more than one language. Most multi-lingual communities worldwide communicate using…”
Get full text