Cover Image

Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Victoria, Xu, Xinnuo, Lawrence, Rachel, Ueno, Risa, Sharma, Amit, Gonzalez, Javier, Prasad, Niranjani
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task
by: Curth, Alicia, et al.
Published: (2026)

RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation
by: Xu, Xinnuo, et al.
Published: (2025)

Reasoning Elicitation in Language Models via Counterfactual Feedback
by: Hüyük, Alihan, et al.
Published: (2024)

Compositional Causal Reasoning Evaluation in Language Models
by: Maasch, Jacqueline R. M. A., et al.
Published: (2025)

Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
by: Azangulov, Iskander, et al.
Published: (2025)

DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning
by: Pandey, Atharva, et al.
Published: (2025)

Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models
by: Du, Chengyu, et al.
Published: (2024)

Causal Reasoning and Large Language Models: Opening a New Frontier for Causality
by: Kıcıman, Emre, et al.
Published: (2023)

AdaptThink: Reasoning Models Can Learn When to Think
by: Zhang, Jiajie, et al.
Published: (2025)

Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code
by: Vashishtha, Aniket, et al.
Published: (2025)

Teaching Transformers Causal Reasoning through Axiomatic Training
by: Vashishtha, Aniket, et al.
Published: (2024)

Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG
by: Khadilkar, Harshad, et al.
Published: (2025)

Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought
by: Chen, Zhikang, et al.
Published: (2025)

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
by: Wan, Xu, et al.
Published: (2025)

Reward Models Identify Consistency, Not Causality
by: Xu, Yuhui, et al.
Published: (2025)

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
by: Zhu, Zihao, et al.
Published: (2025)

Counterfactual Reasoning with Knowledge Graph Embeddings
by: Zellinger, Lena, et al.
Published: (2024)

DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining
by: Zheng, Youze, et al.
Published: (2026)

Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
by: Singh, Joykirat, et al.
Published: (2025)

Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
by: Zhang, Xue, et al.
Published: (2025)

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
by: Xu, Xin, et al.
Published: (2025)

Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced Contexts
by: Ochieng, Millicent, et al.
Published: (2025)

ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
by: Xu, Xin, et al.
Published: (2026)

Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization
by: Wang, Mingyang, et al.
Published: (2024)

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
by: Sun, Chung-En, et al.
Published: (2025)

Train Long, Think Short: Curriculum Learning for Efficient Reasoning
by: Hammoud, Hasan Abed Al Kader, et al.
Published: (2025)

PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
by: Brahman, Faeze, et al.
Published: (2023)

Efficient Reasoning with Hidden Thinking
by: Shen, Xuan, et al.
Published: (2025)

Efficient Reasoning with Balanced Thinking
by: Li, Yulin, et al.
Published: (2026)

Entropy-Aligned Decoding of LMs for Better Writing and Reasoning
by: Ahmed, Kareem, et al.
Published: (2026)

Counterfactual Generation with Identifiability Guarantees
by: Yan, Hanqi, et al.
Published: (2024)

Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds
by: Joishy, Anish R, et al.
Published: (2025)

Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning
by: Qin, Zhanyue, et al.
Published: (2026)

CoRT: Code-integrated Reasoning within Thinking
by: Li, Chengpeng, et al.
Published: (2025)

Optimizing Language Models for Human Preferences is a Causal Inference Problem
by: Lin, Victoria, et al.
Published: (2024)

Asynchronous Reasoning: Training-Free Interactive Thinking LLMs
by: Yakushev, George, et al.
Published: (2025)

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
by: Zheng, Congmin, et al.
Published: (2025)

When Two LLMs Debate, Both Think They'll Win
by: Prasad, Pradyumna Shyama, et al.
Published: (2025)

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
by: Ding, Fei, et al.
Published: (2026)

Thinking Fast, Thinking Wrong: Intuitiveness Modulates LLM Counterfactual Reasoning in Policy Evaluation
by: He, Yanjie
Published: (2026)