3 papers
cs.LG2026
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…
cs.AI2026
Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
Rakshit Trivedi, Kartik Sharma, David C Parkes
Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts. Imitation learning has…
cs.CL2026
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…