Harshita Diddee

PhD student, School of Computer Science, Carnegie Mellon University

Joined

November 2021

Names

Harshita Diddee (Preferred)

Emails

****@gmail.com (Confirmed)

****@microsoft.com (Confirmed)

****@andrew.cmu.edu (Confirmed)

Personal Links

Career & Education History

PhD student

School of Computer Science , Carnegie Mellon University (cmu.edu)

2023 – Present

Intern

Core Search, Amazon (amazon.com)

2025 – 2025

Researcher

Microsoft (microsoft.com)

2021 – 2023

Undergrad student

Bharati Vidyapeeth's College of Engineering (bvp.edu.in)

2017 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Daphne Ippolito

2023 – Present

Expertise

Evaluation Validity

Present

Retail

Present

Benchmark Audit

Present

Meta Evaluation

Present

Natural Language Generation

2023 – Present

Data Quality Estimation

2023 – Present

Publications

NoveltyBench: Evaluating Language Models for Humanlike Diversity
Yiming Zhang, Harshita Diddee, Susan Holm, Hanchen Liu, Xinyue Liu, Vinay Samuel, Barry Wang, Daphne Ippolito
- COLM 2025
- Readers: Everyone
MEGA: Multilingual Evaluation of Generative AI
Kabir Ahuja, Harshita Diddee, Rishav Hada, Millicent Ochieng, Krithika Ramesh, PRACHI JAIN, Akshay Nambi, Tanuja Ganu, Sameer Segal, Mohamed Ahmed, Kalika Bali, Sunayana Sitaram
- 29 Jun 2023 (modified: 29 Jun 2023)
- OpenReview Archive Direct Upload
- Readers: Everyone
"Fifty Shades of Bias": Normative Ratings of Gender Bias in GPT Generated English Text
Rishav Hada, Agrima Seth, Harshita Diddee, Kalika Bali
- EMNLP 2023 Main
- Readers: Everyone
MEGA: Multilingual Evaluation of Generative AI
Kabir Ahuja, Harshita Diddee, Rishav Hada, Millicent Ochieng, Krithika Ramesh, Prachi Jain, Akshay Nambi, Tanuja Ganu, Sameer Segal, Mohamed Ahmed, Kalika Bali, Sunayana Sitaram
- EMNLP 2023 Main
- Readers: Everyone
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
Rishav Hada, Varun Gumma, Adrian de Wynter, Harshita Diddee, Mohamed Ahmed, Monojit Choudhury, Kalika Bali, Sunayana Sitaram
- Published: 01 Jan 2023, Last Modified: 19 Jan 2024
- CoRR 2023
- Readers: Everyone
"Fifty Shades of Bias": Normative Ratings of Gender Bias in GPT Generated English Text
Rishav Hada, Agrima Seth, Harshita Diddee, Kalika Bali
- Published: 01 Jan 2023, Last Modified: 19 Jan 2024
- EMNLP 2023
- Readers: Everyone
The Six Conundrums of Building and Deploying Language Technologies for Social Good
Harshita Diddee, Kalika Bali, Monojit Choudhury, Namrata Mukhija
- 2022 (modified: 04 Oct 2022)
- COMPASS 2022
- Readers: Everyone
Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages
Gowtham Ramesh, Sumanth Doddapaneni, Aravinth Bheemaraj, Mayank Jobanputra, Raghavan AK, Ajitesh Sharma, Sujit Sahoo, Harshita Diddee, Mahalakshmi J, Divyanshu Kakwani, Navneet Kumar, Aswin Pradeep, Srihari Nagaraj, Deepak Kumar, Vivek Raghavan, Anoop Kunchukuttan, Pratyush Kumar, Mitesh Shantadevi Khapra
- 2022 (modified: 28 Jan 2023)
- Trans. Assoc. Comput. Linguistics 2022
- Readers: Everyone
Too Brittle to Touch: Comparing the Stability of Quantization and Distillation towards Developing Low-Resource MT Models
Harshita Diddee, Sandipan Dandapat, Monojit Choudhury, Tanuja Ganu, Kalika Bali
- Published: 01 Jan 2022, Last Modified: 15 May 2023
- WMT 2022
- Readers: Everyone
Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models
Harshita Diddee, Sandipan Dandapat, Monojit Choudhury, Tanuja Ganu, Kalika Bali
- Published: 01 Jan 2022, Last Modified: 15 May 2023
- CoRR 2022
- Readers: Everyone

View all 15 publications

Co-Authors

View all 63 co-authors