State explains 74% of variance in user psychological profiles versus 26% for trait, revealing that LLMs are state-blind and reward models respond inconsistently to the same users.
OliverPJohnandSanjaySrivastava.1999
6 Pith papers cite this work. Polarity classification is still indexing.
verdicts
UNVERDICTED 6representative citing papers
Fine-tuning LLMs on essays reduces variance in IPIP-NEO responses across models but does not raise full five-trait profile accuracy above near-chance levels from unguided text.
Modeling LLM dialogues as bridging-inference knowledge graphs reveals more stable and coherent personas than traditional lexical or stylistic analysis methods.
Simulations show that cooperative outcomes in network games with personality-driven LLM agents depend on both network connectivity and the placement of pro-social personalities, not just pairwise interaction preferences.
Temperature and persona variations shape consensus speed in LLM multi-agent coding but produce no robust accuracy gains over single agents on human-annotated tutoring transcripts.
News users exhibit circadian rhythms at macro scale, power-law session intervals at meso scale, and exponential action timings at micro scale, with clicks primarily driven by historical interests that weaken as content diversity rises.
citing papers explorer
-
Beyond Fixed Psychological Personas: State Beats Trait, but Language Models are State-Blind
State explains 74% of variance in user psychological profiles versus 26% for trait, revealing that LLMs are state-blind and reward models respond inconsistently to the same users.
-
Evaluation Drift in LLM Personality Induction: Are We Moving the Goalpost?
Fine-tuning LLMs on essays reduces variance in IPIP-NEO responses across models but does not raise full five-trait profile accuracy above near-chance levels from unguided text.
-
The Pragmatic Persona: Discovering LLM Persona through Bridging Inference
Modeling LLM dialogues as bridging-inference knowledge graphs reveals more stable and coherent personas than traditional lexical or stylistic analysis methods.
-
NetworkGames: Simulating Cooperation in Network Games with Personality-driven LLM Agents
Simulations show that cooperative outcomes in network games with personality-driven LLM agents depend on both network connectivity and the placement of pro-social personalities, not just pairwise interaction preferences.
-
Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding
Temperature and persona variations shape consensus speed in LLM multi-agent coding but produce no robust accuracy gains over single agents on human-annotated tutoring transcripts.
-
Temporal and Content Coupling Analysis of Social Media User Behavior
News users exhibit circadian rhythms at macro scale, power-law session intervals at meso scale, and exponential action timings at micro scale, with clicks primarily driven by historical interests that weaken as content diversity rises.