Pratik Sachdeva
AI & Society
-
Rating the Raters: Rasch Measurement Theory for LLM Evaluation
-
Why AIs (Might) Obey the Law
-
Interaction Protocol Shapes Moral Judgment in Multi-Agent Debate
-
The Fabricated Front: Generative AI and the Opacity of Workplace Performance
-
The Fragility of Moral Judgment in Large Language Models
-
Normative evaluation of large language models with everyday moral dilemmas
-
Comparing Methods for Estimating Demographics in Racially Polarized Voting Analyses
-
Interrogating Racism in the Medical Literature Using Word Embeddings
-
The stories about racism and health: the development of a framework for racism narratives in medical literature using a computational grounded theory approach
-
Targeted Identity Group Prediction in Hate Speech Corpora
-
The Measuring Hate Speech Corpus: Leveraging Rasch Measurement Theory for Data Perspectivism
-
Assessing Annotator Identity Sensitivity via Item Response Theory: A Case Study in a Hate Speech Corpus
-
Accurate and Scalable Matching of Translators to Displaced Persons for Overcoming Language Barriers
Computational Neuroscience
-
Resolving non-identifiability mitigates systematic errors in simultaneous models of neural tuning and functional coupling
-
The geometry of correlated variability leads to highly suboptimal discriminative sensory coding
-
Improved inference in coupling, encoding, and decoding models and its consequence for neuroscientific interpretation
-
Heterogeneous synaptic weighting improves neural coding in the presence of common noise
-
Sparse, Interpretable, and Predictive Functional Connectomics with UoI-Lasso