A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
Contextual Framing , author=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Stronger reasoning models in LLMs reduce behavioral negotiation by defaulting to authority outcomes in multi-agent settings, unlike structured scaffolds that enable concessions.
A game-theoretic heterogeneous graph network models investor interactions to forecast stock prices and outperforms prior methods on two benchmark datasets.
citing papers explorer
-
Understanding the Mechanism of Altruism in Large Language Models
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
-
When Reasoning Models Hurt Behavioral Simulation: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation
Stronger reasoning models in LLMs reduce behavioral negotiation by defaulting to authority outcomes in multi-agent settings, unlike structured scaffolds that enable concessions.
-
Game-Theoretic Modeling of Heterogeneous Investor Interactions for Stock Price Forecasting
A game-theoretic heterogeneous graph network models investor interactions to forecast stock prices and outperforms prior methods on two benchmark datasets.