activity
20222026
most citedThinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models

1 citations · 1 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CL2026

Learning Through Dialogue: Engagement and Efficacy Matter More Than Explanations

Shaz Furniturewala, Gerard Christopher Yeo, Kokil Jaidka

Large language models (LLMs) are increasingly used as conversational partners for learning, yet the interactional dynamics supporting users' learning and engagement are understudie…

cs.CL2025

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content

Shaz Furniturewala, Arkaitz Zubiaga

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation sy…

cs.CL2024

Impact of Decoding Methods on Human Alignment of Conversational LLMs

Shaz Furniturewala, Kokil Jaidka, Yashvardhan Sharma

To be included into chatbot systems, Large language models (LLMs) must be aligned with human conversational conventions. However, being trained mainly on web-scraped data gives exi…

cs.CL2024

Turn-Level Empathy Prediction Using Psychological Indicators

Shaz Furniturewala, Kokil Jaidka

For the WASSA 2024 Empathy and Personality Prediction Shared Task, we propose a novel turn-level empathy detection method that decomposes empathy into six psychological indicators:…

cs.CL2024

Beyond Text: Leveraging Multi-Task Learning and Cognitive Appraisal Theory for Post-Purchase Intention Analysis

Gerard Christopher Yeo, Shaz Furniturewala, Kokil Jaidka

Supervised machine-learning models for predicting user behavior offer a challenging classification problem with lower average prediction performance scores than other text classifi…

cs.CL2024★ 1 cited

Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models

Shaz Furniturewala, Surgan Jandial, Abhinav Java +4

Existing debiasing techniques are typically training-based or require access to the model's internals and output distributions, so they are inaccessible to end-users looking to ada…