Pragyan Banerjee — accepted AI-conference papers

2024

All Should Be Equal in the Eyes of LMs: Counterfactually Aware Fair Text Generation

Pragyan Banerjee, Abhinav Java, Surgan Jandial, Simra Shahid, Shaz Furniturewala, Balaji Krishnamurthy +1

AAAI 2024technical

Fairness in Language Models (LMs) remains a long-standing challenge, given the inherent biases in training data that can be perpetuated by models and affect the downstream tasks. Recent methods employ expensive retraining or attempt debiasing during inference by constraining model outputs to contras…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

Evaluating the Efficacy of Prompting Techniques for Debiasing Language Model Outputs (Student Abstract)

Shaz Furniturewala, Surgan Jandial, Abhinav Java, Simra Shahid, Pragyan Banerjee, Balaji Krishnamurthy +2

AAAI 2024technical

Achieving fairness in Large Language Models (LLMs) continues to pose a persistent challenge, as these models are prone to inheriting biases from their training data, which can subsequently impact their performance in various applications. There is a need to systematically explore whether structured…

Cited by 2 Source ↗PDF ↗Scholar ↗

2024

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

Shaz Furniturewala, Surgan Jandial, Abhinav Java, Pragyan Banerjee, Simra Shahid, Sumit Bhatia +1

EMNLP 2024main

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 adapt LLM outputs for their particular needs. In this study, we examine whether structured prompting techniques can offer o…

Cited by 11 Source ↗PDF ↗Scholar ↗