7 papers
COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
Kartik Sharma, Rakshit S. Trivedi
Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-eff…
Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
Kartik Sharma, Yiqiao Jin, Vineeth Rakesh +4
As large language models (LLMs) are deployed in safety-critical settings, it is essential to ensure that their responses comply with safety standards. Prior research has revealed t…
Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings
Kartik Sharma, Yiqiao Jin, Rakshit Trivedi +1
Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stoc…
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
Yiqiao Jin, Kartik Sharma, Vineeth Rakesh +4
Retrieval-augmented Generation (RAG) extends large language models (LLMs) with external knowledge but faces key challenges: restricted effective context length and redundancy in re…
Personalized Layer Selection for Graph Neural Networks
Kartik Sharma, Vineeth Rakesh, Yingtong Dou +2
Graph Neural Networks (GNNs) combine node attributes over a fixed granularity of the local graph structure around a node to predict its label. However, different nodes may relate t…
A Thousand Words or An Image: Studying the Influence of Persona Modality in Multimodal LLMs
Julius Broomfield, Kartik Sharma, Srijan Kumar
Large language models (LLMs) have recently demonstrated remarkable advancements in embodying diverse personas, enhancing their effectiveness as conversational agents and virtual as…