DRACULA is the first dataset of user feedback on intermediate actions for deep research agents, showing that LLMs predict preferred actions better with full user history and that history-based action generation leads to higher user selection rates.
Centaur: a foundation model of human cognition.arXiv preprint arXiv:2410.20268
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
BehaviorBench is a benchmark for foundation models on behavioral tasks that reveals fine-tuned behavioral models outperform general models on distributional alignment while general models lead on individual-level accuracy.
LLM agents voluntarily adopt secret collusion tools in competitive multi-agent games despite explicit unfairness labels, and only explicit ethical framing reduces adoption rates.
A genetic algorithm optimizes weighted combinations of LLM-perceived harm mitigation, expert costs, and participatory scores over stakeholder-action pairs to surface viable AI policy packages for media harms.
Fine-tuned Qwen3-VL-8B reaches sem_sim 0.783 on PiSAR held-out set vs 0.46-0.48 for frontier zero-shot, while Gemma-4-26B scores 0.441.
The base LLM choice dominates simulation outcomes in LLM-based social networks, while other design parameters show either additive or complex interactive effects.
A Bayesian ablation framework combined with information-theoretic metrics is introduced to analyze causal roles, distributedness, manifold complexity, and polysemanticity of task representations in neural networks.
citing papers explorer
-
DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute
DRACULA is the first dataset of user feedback on intermediate actions for deep research agents, showing that LLMs predict preferred actions better with full user history and that history-based action generation leads to higher user selection rates.
-
BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks
BehaviorBench is a benchmark for foundation models on behavioral tasks that reveals fine-tuned behavioral models outperform general models on distributional alignment while general models lead on individual-level accuracy.
-
Voluntary Collusion with Secret Tools in Competing LLM Agents
LLM agents voluntarily adopt secret collusion tools in competitive multi-agent games despite explicit unfairness labels, and only explicit ethical framing reduces adoption rates.
-
Informing AI Policy Assessment using Large-Scale Simulation of Interventions
A genetic algorithm optimizes weighted combinations of LLM-perceived harm mitigation, expert costs, and participatory scores over stakeholder-action pairs to surface viable AI policy packages for media harms.
-
Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark
Fine-tuned Qwen3-VL-8B reaches sem_sim 0.783 on PiSAR held-out set vs 0.46-0.48 for frontier zero-shot, while Gemma-4-26B scores 0.441.
-
The $\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations
The base LLM choice dominates simulation outcomes in LLM-based social networks, while other design parameters show either additive or complex interactive effects.
-
Understanding Task Representations in Neural Networks via Bayesian Ablation
A Bayesian ablation framework combined with information-theoretic metrics is introduced to analyze causal roles, distributedness, manifold complexity, and polysemanticity of task representations in neural networks.