Harshita Diddee

28 papers A* 4B 1C 1Journal 16Unranked 6
YearRankTypeTitle / Venue / Authors
2026 J jnl
BenchBrowser - Collecting Evidence for Evaluating Benchmark Validity.
CoRR
Harshita Diddee, Gregory Yauney, Swabha Swayamdipta, Daphne Ippolito
2025 A* conf
CIE: Controlling Language Model Text Generations Using Continuous Signals.
EMNLP
Vinay Samuel, Harshita Diddee, Yiming Zhang, Daphne Ippolito
2025 J jnl
CIE: Controlling Language Model Text Generations Using Continuous Signals.
CoRR
Vinay Samuel, Harshita Diddee, Yiming Zhang, Daphne Ippolito
2025 — conf
Chasing Random: Instruction Selection Strategies Fail to Generalize.
NAACL (Findings)
Harshita Diddee, Daphne Ippolito
2025 J jnl
NoveltyBench: Evaluating Language Models for Humanlike Diversity.
CoRR
Yiming Zhang, Harshita Diddee, Susan Holm, Hanchen Liu, Xinyue Liu, Vinay Samuel, Barry Wang, Daphne Ippolito
2024 — conf
Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology.
FAccT
Rishav Hada, Safiya Husain, Varun Gumma, Harshita Diddee, Aditya Yadavalli, Agrima Seth, Nidhi Kulkarni, Ujwal Gadiraju, Aditya Vashistha, Vivek Seshadri, Kalika Bali
2024 J jnl
Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology.
CoRR
Rishav Hada, Safiya Husain, Varun Gumma, Harshita Diddee, Aditya Yadavalli, Agrima Seth, Nidhi Kulkarni, Ujwal Gadiraju, Aditya Vashistha, Vivek Seshadri, Kalika Bali
2024 — conf
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
EACL (Findings)
Rishav Hada, Varun Gumma, Adrian de Wynter, Harshita Diddee, Mohamed Ahmed, Monojit Choudhury, Kalika Bali, Sunayana Sitaram
2024 J jnl
Chasing Random: Instruction Selection Strategies Fail to Generalize.
CoRR
Harshita Diddee, Daphne Ippolito
2024 J jnl
CodeFed: Federated Speech Recognition for Low-Resource Code-Switching Detection.
ACM Trans. Asian Low Resour. Lang. Inf. Process.
Chetan Madan, Harshita Diddee, Deepika Kumar, Mamta Mittal
2024 B conf
Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning.
INLG
Xinyue Liu, Harshita Diddee, Daphne Ippolito
2024 J jnl
Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning.
CoRR
Xinyue Liu, Harshita Diddee, Daphne Ippolito
2024 — conf
INMT-Lite: Accelerating Low-Resource Language Data Collection via Offline Interactive Neural Machine Translation.
LREC/COLING
Harshita Diddee, Anurag Shukla, Tanuja Ganu, Vivek Seshadri, Sandipan Dandapat, Monojit Choudhury, Kalika Bali
2023 A* conf
"Fifty Shades of Bias": Normative Ratings of Gender Bias in GPT Generated English Text.
EMNLP
Rishav Hada, Agrima Seth, Harshita Diddee, Kalika Bali
2023 J jnl
"Fifty Shades of Bias": Normative Ratings of Gender Bias in GPT Generated English Text.
CoRR
Rishav Hada, Agrima Seth, Harshita Diddee, Kalika Bali
2023 J jnl
Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?
CoRR
Rishav Hada, Varun Gumma, Adrian de Wynter, Harshita Diddee, Mohamed Ahmed, Monojit Choudhury, Kalika Bali, Sunayana Sitaram
2023 A* conf
MEGA: Multilingual Evaluation of Generative AI.
EMNLP
Kabir Ahuja, Harshita Diddee, Rishav Hada, Millicent Ochieng, Krithika Ramesh, Prachi Jain, Akshay Uttama Nambi, Tanuja Ganu, Sameer Segal, Mohamed Ahmed, Kalika Bali, Sunayana Sitaram
2023 J jnl
MEGA: Multilingual Evaluation of Generative AI.
CoRR
Kabir Ahuja, Rishav Hada, Millicent Ochieng, Prachi Jain, Harshita Diddee, Samuel C. Maina, Tanuja Ganu, Sameer Segal, Maxamed Axmed, Kalika Bali, Sunayana Sitaram
2022 J jnl
Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi.
CoRR
Devansh Mehta, Harshita Diddee, Ananya Saxena, Anurag Shukla, Sebastin Santy, Ramaravind Kommiya Mothilal, Brij Mohan Lal Srivastava, Alok Sharma, Vishnu Prasad, Venkanna U, Kalika Bali
2022 J jnl
Native accent Sensitive voice cloning using Pairwise Ranking based decoder Models.
Mechatron. Syst. Control.
Chetan Madan, Harshita Diddee, Deepika Kumar, Shilpa Gupta, Shivani Jindal, Mansi Lal, Chiranjeev
2022 J jnl
Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages.
Trans. Assoc. Comput. Linguistics
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 C conf
The Six Conundrums of Building and Deploying Language Technologies for Social Good.
COMPASS
Harshita Diddee, Kalika Bali, Monojit Choudhury, Namrata Mukhija
2022 J jnl
Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models.
CoRR
Harshita Diddee, Sandipan Dandapat, Monojit Choudhury, Tanuja Ganu, Kalika Bali
2022 — conf
Too Brittle to Touch: Comparing the Stability of Quantization and Distillation towards Developing Low-Resource MT Models.
WMT
Harshita Diddee, Sandipan Dandapat, Monojit Choudhury, Tanuja Ganu, Kalika Bali
2021 J jnl
Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages.
CoRR
Gowtham Ramesh, Sumanth Doddapaneni, Aravinth Bheemaraj, Mayank Jobanputra, Raghavan AK, Ajitesh Sharma, Sujit Sahoo, Harshita Diddee, Mahalakshmi J, Divyanshu Kakwani, Navneet Kumar, Aswin Pradeep, Deepak Kumar, Vivek Raghavan, Anoop Kunchukuttan, Pratyush Kumar, Mitesh Shantadevi Khapra
2021 J jnl
Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning.
CoRR
Rakshit Naidu, Harshita Diddee, Ajinkya Mulay, Aleti Vardhan, Krithika Ramesh, Ahmed S. Zamzam
2020 A* conf
CrossPriv: User Privacy Preservation Model for Cross-Silo Federated Software.
ASE
Harshita Diddee, Bhrigu Kansra
2020 — conf
PsuedoProp at SemEval-2020 Task 11: Propaganda Span Detection Using BERT-CRF and Ensemble Sentence Level Classifier.
SemEval@COLING
Aniruddha Chauhan, Harshita Diddee