6 papers
On Scope Classification and Current Knowledge-Editing Benchmarks: A Negative Result, with INLAY as a Gradient-Free Case Study
Aditya Pratap Singh
Every memory-based knowledge editor in the SERAC lineage depends on a scope decision: given a query, does a stored edit apply? We report that current knowledge-editing benchmarks c…
Conversational Domain Adaptation of IndicTrans2 across 21 Indic Languages via Experience Replay and Model Soups
Aditya Pratap Singh
IndicTrans2 is the strongest open English to Indic translation system, but like most systems it is trained on general text and tends to sound stiff on casual, conversational input.…
Automatically Finding Rule-Based Neurons in OthelloGPT
Aditya Singh, Zihang Wen, Srujananjali Medicherla +2
OthelloGPT, a transformer trained to predict valid moves in Othello, provides an ideal testbed for interpretability research. The model is complex enough to exhibit rich computatio…
Concept Incongruence: An Exploration of Time and Death in Role Playing
Xiaoyan Bai, Ike Peng, Aditya Singh +1
Consider this prompt "Draw a unicorn with two horns". Should large language models (LLMs) recognize that a unicorn has only one horn by definition and ask users for clarifications,…
X-lifecycle Learning for Cloud Incident Management using LLMs
Drishti Goel, Fiza Husain, Aditya Singh +5
Incident management for large cloud services is a complex and tedious process and requires significant amount of manual efforts from on-call engineers (OCEs). OCEs typically levera…
Optimizing performance in Basketball: A Game-Theoretic Approach to Shot Percentage Distribution in a team
Aditya Singh
In this paper, we propose a shot percentage distribution strategy among the players of a basketball team to maximize the score that can be achieved by them. The approach is based o…