Image de couverture de livre

Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Vashishtha, Aniket, Dai, Qirun, Mei, Hongyuan, Sharma, Amit, Tan, Chenhao, Peng, Hao
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Realizing LLMs' Causal Potential Requires Science-Grounded, Novel Benchmarks
par: Srivastava, Ashutosh, et autres
Publié: (2025)

Teaching Transformers Causal Reasoning through Axiomatic Training
par: Vashishtha, Aniket, et autres
Publié: (2024)

Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning
par: You, Zhiwen, et autres
Publié: (2026)

Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
par: Kıcıman, Emre, et autres
Publié: (2023)

The Best Instruction-Tuning Data are Those That Fit
par: Zhang, Dylan, et autres
Publié: (2025)

Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
par: Dai, Qirun, et autres
Publié: (2025)

Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency
par: Lin, Victoria, et autres
Publié: (2026)

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists
par: Yang, Junlin, et autres
Publié: (2026)

Generalization of RLVR Using Causal Reasoning as a Testbed
par: Lu, Brian, et autres
Publié: (2025)

CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation
par: Khatibi, Elahe, et autres
Publié: (2026)

Barriers to Counterfactual Credit Attribution for Autoregressive Models
par: Cohen, Aloni, et autres
Publié: (2026)

Hypothesis Generation with Large Language Models
par: Zhou, Yangqiaoyu, et autres
Publié: (2024)

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
par: Wang, Jingyao, et autres
Publié: (2026)

Improving Generative Methods for Causal Evaluation via Simulation-Based Inference
par: Amaranath, Pracheta, et autres
Publié: (2025)

CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions
par: Heddaya, Mourad, et autres
Publié: (2024)

Code-Guided Reasoning for Small Language Models: Evaluating Executable MCQA Scaffolds
par: Biswas, Prateek, et autres
Publié: (2026)

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation
par: Yu, Zhuohao, et autres
Publié: (2024)

Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoning
par: Yamin, Khurram, et autres
Publié: (2025)

Learning Counterfactually Fair Models via Improved Generation with Neural Causal Models
par: Kher, Krishn Vishwas, et autres
Publié: (2025)

Self-Execution Simulation Improves Coding Models
par: Maimon, Gallil, et autres
Publié: (2026)

Decision Focused Causal Learning for Direct Counterfactual Marketing Optimization
par: Zhou, Hao, et autres
Publié: (2024)

Leveraging priors on distribution functions for multi-arm bandits
par: Vashishtha, Sumit, et autres
Publié: (2025)

Federated Causal Representation Learning in State-Space Systems for Decentralized Counterfactual Reasoning
par: Mohamed, Nazal, et autres
Publié: (2026)

DiffusionCounterfactuals: Inferring High-dimensional Counterfactuals with Guidance of Causal Representations
par: Zhu, Jiageng, et autres
Publié: (2024)

$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
par: Wang, Peihao, et autres
Publié: (2026)

Out-of-Distribution Adaptation in Offline RL: Counterfactual Reasoning via Causal Normalizing Flows
par: Cho, Minjae, et autres
Publié: (2024)

Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples
par: Cai, Ruichu, et autres
Publié: (2023)

CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
par: Gu, Alex, et autres
Publié: (2024)

Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs
par: Haque, Mirazul, et autres
Publié: (2025)

CARE: Turning LLMs Into Causal Reasoning Expert
par: Dong, Juncheng, et autres
Publié: (2025)

Failure Modes of LLMs for Causal Reasoning on Narratives
par: Yamin, Khurram, et autres
Publié: (2024)

Causal and Counterfactual Views of Missing Data Models
par: Nabi, Razieh, et autres
Publié: (2022)

Understanding Lookahead Dynamics Through Laplace Transform
par: Sanyal, Aniket, et autres
Publié: (2025)

$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
par: Zhang, Dylan, et autres
Publié: (2024)

CausalBench: A Comprehensive Benchmark for Causal Learning Capability of LLMs
par: Zhou, Yu, et autres
Publié: (2024)

The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research
par: Bai, Xiaoyan, et autres
Publié: (2026)

The Double Life of Code World Models: Provably Unmasking Malicious Behavior Through Execution Traces
par: Sahoo, Subramanyam
Publié: (2025)

Towards Verified Code Reasoning by LLMs
par: Sistla, Meghana, et autres
Publié: (2025)

Causal Micro-Narratives
par: Heddaya, Mourad, et autres
Publié: (2024)

Certifying Counterfactual Bias in LLMs
par: Chaudhary, Isha, et autres
Publié: (2024)