Temporal preference in Qwen3-4B-Instruct-2507 localizes to layers 17–35 (especially L24 attention), has curved residual-stream geometry, is behaviorally unstable, and can be bidirectionally steered.
Llm economicus? mapp ing the behavioral biases of llms via utility theory
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Using 85 controlled and 35 public LLMs, the authors show social-simulation accuracy generally improves with compute, but some behavioral and low-resource tasks do not scale.
A survey synthesizing recent LLM research and assessing its applicability to financial data analysis.
citing papers explorer
-
Temporal Preference Concepts and their Functions in a Large Language Model
Temporal preference in Qwen3-4B-Instruct-2507 localizes to layers 17–35 (especially L24 attention), has curved residual-stream geometry, is behaviorally unstable, and can be bidirectionally steered.
-
Will Scaling Improve Social Simulation with LLMs?
Using 85 controlled and 35 public LLMs, the authors show social-simulation accuracy generally improves with compute, but some behavioral and low-resource tasks do not scale.
-
Bridging Language Models and Financial Analysis
A survey synthesizing recent LLM research and assessing its applicability to financial data analysis.