2 papers
cs.CL2026
The Story Shapes the Agent: Narrative Priors in LLM Behavior
Yixuan Wang, James Lester, Shashank Srivastava
Persona prompting is widely used to steer LLM agent behavior, yet the narrative framing of a task can matter more than the assigned persona. We isolate this effect through structur…
cs.LG2025
MarginSel : Max-Margin Demonstration Selection for LLMs
Rajeev Bhatt Ambati, James Lester, Shashank Srivastava +1
Large Language Models (LLMs) excel at few-shot learning via in-context learning (ICL). However, the effectiveness of ICL is often sensitive to the selection and ordering of demonst…