IV-ICL learns the marginal posterior of causal effects via in-context learning to derive bounds as quantiles, recovering the identified set more reliably than variational inference while running 20-500x faster.
Towards causal foundation model: On duality between causal inference and attention
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Amortized transformer model with conditional fixed-point iterations learns SCM causal mechanisms from data and graphs, matching per-dataset baselines and outperforming in low-data regimes.
Supervised fine-tuning of pretrained LLMs on offline trajectories yields better few-shot sequential decision-making than in-context-only baselines, with a theoretical suboptimality bound derived for linear MDPs by interpreting attention as Q-function estimation.
citing papers explorer
-
IV-ICL: Bounding Causal Effects with Instrumental Variables via In-Context Learning
IV-ICL learns the marginal posterior of causal effects via in-context learning to derive bounds as quantiles, recovering the identified set more reliably than variational inference while running 20-500x faster.
-
Amortized Inference of Causal Models via Conditional Fixed-Point Iterations
Amortized transformer model with conditional fixed-point iterations learns SCM causal mechanisms from data and graphs, matching per-dataset baselines and outperforming in low-data regimes.
-
Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning
Supervised fine-tuning of pretrained LLMs on offline trajectories yields better few-shot sequential decision-making than in-context-only baselines, with a theoretical suboptimality bound derived for linear MDPs by interpreting attention as Q-function estimation.