2 citations · 3 across the 2 of their papers we have counts for
3 papers
PEARL: Prediction Error-Adaptive Regularized Learning for Selective Forgetting under Partial Preference Drift
Rashmi Gangadharaiah, Balakrishnan Narayanaswamy
User preferences shift as needs, context, and tastes evolve. This matters for personalized recommendation, LLM response generation, and RLHF-trained reward models, which can become…
Zero-Shot Learning for Joint Intent and Slot Labeling
Rashmi Gangadharaiah, Balakrishnan Narayanaswamy
It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Languag…
Achieving Fluency and Coherency in Task-oriented Dialog
Rashmi Gangadharaiah, Balakrishnan Narayanaswamy, Charles Elkan
We consider real world task-oriented dialog settings, where agents need to generate both fluent natural language responses and correct external actions like database queries and up…