Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
Rotem Dror, Zohar Elyoseph, Yuval Haber +3
Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent character behavior across ex…
cs.CL2025
State over Tokens: Characterizing the Role of Reasoning Tokens
Mosh Levy, Zohar Elyoseph, Shauli Ravfogel +1
Large Language Models (LLMs) can generate reasoning tokens before their final answer to boost performance on complex tasks. While these sequences seem like human thought processes,…