3 papers
cs.AI2026
Large Language Models Can Take False First Steps at Inference-time Planning
Haijiang Yan, Jian-Qiao Zhu, Adam Sanborn
Large language models (LLMs) have been shown to acquire sequence-level planning abilities during training, yet their planning behavior exhibited at inference time often appears sho…
cs.CL2025
Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations
Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths
Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." Th…
cs.CL2025
Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints
Jian-Qiao Zhu, Haijiang Yan, Thomas L. Griffiths
Rational decision-making under uncertainty requires coherent degrees of belief in events. However, event probabilities generated by Large Language Models (LLMs) have been shown to…