Register and share your invite link to earn from video plays and referrals.

Search results for CausalInference
CausalInference community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including CausalInference
TL;DR: Causal foundation models can report sound intervals per unit, yet become overconfident on group averages. The cause is aggregation that ignores correlated unit errors. Unit-level aggregation breaks coverage in causal foundation models Key points ・🎯 For the full-sample average effect on ACIC 2016, CausalPFN's calibrated 95% interval contained the truth in only 8 of 40 datasets ・🧮 The cause is correlated unit errors: variance is inflated by 1+(k−1)ρ (the design effect), yet units were summed as if independent ・🔁 The fix is SCM-marginalized aggregation: units within a draw share one causal model ・🧠 Approximated with small CNP and latent NP models, also usable as heads on a frozen CausalPFN ・📈 Full-sample coverage across 240 datasets on 6 benchmarks is about 90% (CausalPFN: 53%) ・⚠️ The cost: lower unit-level accuracy on 3 benchmarks and wider intervals If decisions rely on group averages, how uncertainty is aggregated deserves as much scrutiny as the point estimate. #CausalInference# #FoundationModels#
Show more
Congratulations to seven research projects that were selected for the Spring 2026 cohort. - Emmanuel Candès, Stanford University: Statistically Efficient LLM Evaluation and Ranking with Pairwise Human Preference Data - Haifeng Xu @haifengxu0, University of Chicago: Towards a Principled Evaluation of LLMs’ Predictive Intelligence - Lihua Lei @lihua_lei_stat, Stanford University: Is Bradley–Terry Enough? Heterogeneous Preference Modeling for RLHF - Negin Golrezaei @NeginGolrezaei, Massachusetts Institute of Technology: Causal inference framework for multi-turn AI evaluation. - Ramesh Raskar @raskarmit, Massachusetts Institute of Technology: Toward Adaptive, Task-Conditional Evaluation for AI Agents - Steven Wu @zstevenwu and Andrew Ilyas @andrew_ilyas, Carnegie Mellon University: Goodhart’s Law on the Leaderboard: Can Cheap Preference Optimization Game Arena? -Tal Linzen @tallinzen, New York University: A Rigorous Evaluation of Meta-Cognitive Monitoring in LLMs Read more about the program details and submit your proposal for Fall 2026 here:
Show more