8 papers
Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs
Ayush Gupta, Ramneet Kaur, Anirban Roy +3
We propose a novel inference-time out-of-domain (OOD) detection algorithm for specialized large language models (LLMs). Despite achieving state-of-the-art performance on in-domain…
Privacy Preserving In-Context-Learning Framework for Large Language Models
Bishnu Bhusal, Manoj Acharya, Ramneet Kaur +5
Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive in…
TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision
Ayush Gupta, Anirban Roy, Rama Chellappa +3
We address the problem of video question answering (video QA) with temporal grounding in a weakly supervised setup, without any temporal annotations. Given a video and a question,…
Calibrating Uncertainty Quantification of Multi-Modal LLMs using Grounding
Trilok Padhi, Ramneet Kaur, Adam D. Cobb +7
We introduce a novel approach for calibrating uncertainty quantification (UQ) tailored for multi-modal large language models (LLMs). Existing state-of-the-art UQ methods rely on co…
Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarios
Vivian Lin, Ramneet Kaur, Yahan Yang +6
The safety of learning-enabled cyber-physical systems is compromised by the well-known vulnerabilities of deep neural networks to out-of-distribution (OOD) inputs. Existing literat…
TeleLoRA: Teleporting Model-Specific Alignment Across LLMs
Xiao Lin, Manoj Acharya, Anirban Roy +1
Mitigating Trojans in Large Language Models (LLMs) is one of many tasks where alignment data is LLM specific, as different LLMs have different Trojan triggers and trigger behaviors…