36 citations · 393 across the 141 of their papers we have counts for
153 papers
Can Data Attribution Filter Out Subliminal Learning? Not Reliably
Moritz Weckbecker, Sweta Jena, Jonas Müller +5
Subliminal learning allows language models to transmit behavioral traits through training data with no obvious semantic relationship to those traits, undermining content-based data…
MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning
Ashok Urlana, L. D. M. S. Sai Teja, Vivek Hruday Kavuri +1
We present our submission to Task 3 of the Gen 2.0 Challenge on visual concept unlearning. Building on MapRoute, we introduce task-specific training objectives, richer concept r…
CPO: Evaluating Cross-Modal Composition and Counterfactual Performance in Omnimodal Models
Swapnanil Mukherjee, Agyeya Negi, Tanuja Ganu +1
Current Multimodal Large Language Models (MLLMs) can process diverse sensory inputs, yet their reasoning remains heavily biased toward a dominant modality, resulting in brittle cro…
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…
GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods
Sujay Belsare, Sudarshan Nikhil, Sushant Kumar +2
With the increasing development of Vision-Language Models, it becomes imperative that their predictions are readily explainable to relevant stakeholders. However, the field of expl…
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
Krishak Aneja, Manas Mittal, Anmol Goel +2
Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work lin…