Official implementation of our EMNLP 2022 paper "CPL: Counterfactual Prompt Learning for Vision and Language Models"
The first counterfactual PL semantics dataset for evaluating rule-conditioned reasoning in LLMs
Resources for our AAAI 2022 paper: "Unsupervised Editing for Counterfactual Stories".
MagicBench: A Deception-Sensitive Cognitive Benchmark for LLMs
Tensorflow implementation of "Learn-Explain-Reinforce: Counterfactual Reasoning and Its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model" [IEEE TPAMI 2023]
A counterfactual network digital twin for safe agentic remediation in multi-tenant AI data-center fabrics: action-conditioned causal inference, uncertainty-aware safety gate, and verified rollback.
Course materials for Causal Intelligence: causal inference, causal discovery, causal machine learning, counterfactual reasoning, robust AI, explainable AI, and decision intelligence.
Paper titled "On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Study" was accepted (poster) by ICLR 2026
Research proposal, no code yet: forecasting that starts from probabilistic future scenarios and works backward to present decisions, combining Bayesian networks, counterfactual reasoning, MDPs and reinforcement learning.
a process-first relational programming language
World-model-based molecular optimization with counterfactual planning and 2,500× oracle savings.
Benchmark for observer-participant failure and counterfactual trustworthiness in agentic AI.
Counterfactual attribution for multi-agent LLM failures - find which message broke the system, not which agent.
Environment-authoritative multi-agent simulation & trajectory-data system. LLMs & agents only propose; a deterministic world adjudicates every consequence.
[NeurIPS 2023] Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation. https://arxiv.org/abs/2310.17146
🧠 Causal Digital Twin for Marketing at Scale · Predict any marketing decision before you spend a dollar.
Official code for "Counterfactual Residual Data Augmentation for Regression" (ICML 2026) — a model-agnostic augmentation method for tabular regression under data scarcity.
An interactive scientific illustration & visual flight recorder for observable AI agent behavior. Step-by-step cognitive tracing, counterfactual branching, and dynamic focus.
Deterministic epistemic investigation core, causal hypothesis exploration engine, and strategic-network benchmark evaluating structured causal reasoning against monolithic LLM baselines.
Counterfactual validation for autonomous driving
To associate your repository with the counterfactual-reasoning topic, visit your repo's landing page and select "manage topics."