Akshita Jha

18 papers A* 1A 1Journal 10Unranked 5
YearRankTypeTitle / Venue / Authors
2025 — —
Adversarial Risks and Stereotype Mitigation at Scale in Generative Models.
Akshita Jha
2025 A conf
Examining Age-Bias and Stereotypes of Aging in LLMs.
ASSETS
Sherwin Dewan, Ismail Shaikh, Connie Shaw, Abhilash Sahoo, Akshita Jha, Alisha Pradhan
2025 — conf
Examining and Mitigating Ability-bias in LLMs via Self-Reflection.
W4A
Neel Iyer, Akshita Jha, Alisha Pradhan
2025 J jnl
PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming.
CoRR
Wesley Hanwen Deng, Sunnie S. Y. Kim, Akshita Jha, Ken Holstein, Motahhare Eslami, Lauren Wilcox, Leon A. Gatys
2025 J jnl
Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning.
CoRR
Sanchit Kabra, Akshita Jha, Chandan K. Reddy
2024 J jnl
Beyond the Surface: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation.
CoRR
Akshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo, Shachi Dave, Rida Qadri, Chandan K. Reddy, Sunipa Dev
2024 J jnl
Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws.
CoRR
Akshita Jha, Sanchit Kabra, Chandan K. Reddy
2024 — conf
ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation.
ACL (1)
Akshita Jha, Vinodkumar Prabhakaran, Remi Denton, Sarah Laszlo, Shachi Dave, Rida Qadri, Chandan K. Reddy, Sunipa Dev
2023 A* conf
CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Models.
AAAI
Akshita Jha, Chandan K. Reddy
2023 — conf
SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models.
ACL (1)
Akshita Jha, Aida Mostafazadeh Davani, Chandan K. Reddy, Shachi Dave, Vinodkumar Prabhakaran, Sunipa Dev
2023 J jnl
SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models.
CoRR
Akshita Jha, Aida Mostafazadeh Davani, Chandan K. Reddy, Shachi Dave, Vinodkumar Prabhakaran, Sunipa Dev
2023 J jnl
Supervised Contrastive Learning for Interpretable Long-Form Document Matching.
ACM Trans. Knowl. Discov. Data
Akshita Jha, Vineeth Rakesh, Jaideep Chandrashekar, Adithya Samavedhi, Chandan K. Reddy
2023 — conf
Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis.
EACL (Findings)
Akshita Jha, Adithya Samavedhi, Vineeth Rakesh, Jaideep Chandrashekar, Chandan K. Reddy
2023 J jnl
Transformer-based Models for Long-Form Document Matching: Challenges and Empirical Analysis.
CoRR
Akshita Jha, Adithya Samavedhi, Vineeth Rakesh, Jaideep Chandrashekar, Chandan K. Reddy
2022 J jnl
CodeAttack: Code-based Adversarial Attacks for Pre-Trained Programming Language Models.
CoRR
Akshita Jha, Chandan K. Reddy
2021 J jnl
Fair Representation Learning using Interpolation Enabled Disentanglement.
CoRR
Akshita Jha, Bhanukiran Vinzamuri, Chandan K. Reddy
2021 J jnl
Supervised Contrastive Learning for Interpretable Long Document Comparison.
CoRR
Akshita Jha, Vineeth Rakesh, Jaideep Chandrashekar, Adithya Samavedhi, Chandan K. Reddy
2017 — conf
When does a compliment become sexist? Analysis and classification of ambivalent sexism using twitter data.
NLP+CSS@ACL
Akshita Jha, Radhika Mamidi