36 citations · 393 across the 141 of their papers we have counts for
17 papers · 1 filter
OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization
Kavin Aravindan, Arihant Rastogi, Krishak Aneja +4
Activation steering provides a lightweight mechanism for controlling large language models at inference time, but steering vectors can have unintended externalities: utility vector…
Sample Complexity of Causal Identification with Temporal Heterogeneity
Ameya Rathod, Sujay Belsare, Salvik Krishna Nautiyal +2
Recovering a unique causal graph from observational data is an ill-posed problem because multiple generating mechanisms can lead to the same observational distribution. This proble…
MetaGMT: Improving Actionable Interpretability of Graph Multilinear Networks via Meta-Learning Filtration
Rishabh Bhattacharya, Hari Shankar, Vaishnavi Shivkumar +1
The growing adoption of Graph Neural Networks (GNNs) in high-stakes domains like healthcare and finance demands reliable explanations of their decision-making processes. While inhe…
Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation
Shiven Sinha, Shashwat Goel, Ponnurangam Kumaraguru +3
There is growing excitement about the potential of Language Models (LMs) to accelerate scientific discovery. Falsifying hypotheses is key to scientific progress, as it allows claim…
SPIRIT: Short-term Prediction of solar IRradIance for zero-shot Transfer learning using Foundation Models
Aditya Mishra, Ravindra T, Srinivasan Iyengar +2
Traditional solar forecasting models are based on several years of site-specific historical irradiance data, often spanning five or more years, which are unavailable for newer phot…
Great Models Think Alike and this Undermines AI Oversight
Shashwat Goel, Joschka Struber, Ilze Amanda Auzina +6
As Language Model (LM) capabilities advance, evaluating and supervising them at scale is getting harder for humans. There is hope that other language models can automate both these…