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

arXiv: https://arxiv.org/abs/2602.16787 · HTML: https://mlsanity.com/paper/2602.16787/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 12 of 12)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [TTRL: Test-Time Reinforcement Learning](https://mlsanity.com/paper/2504.16084/) (2025)
- [Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs](https://mlsanity.com/paper/2402.11199/) (2024)
- [CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models](https://mlsanity.com/paper/2502.11008/) (2025)
- [Counterfactual Token Generation in Large Language Models](https://mlsanity.com/paper/2409.17027/) (2024)
- [Reasoning Elicitation in Language Models via Counterfactual Feedback](https://mlsanity.com/paper/2410.03767/) (2024)
- [Gumbel Counterfactual Generation From Language Models](https://mlsanity.com/paper/2411.07180/) (2024)
- [Self-Consistency Boosts Calibration for Math Reasoning](https://mlsanity.com/paper/2403.09849/) (2024)
- [Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models](https://mlsanity.com/paper/2502.11425/) (2025)
- [DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning](https://mlsanity.com/paper/2504.07080/) (2025)

## Abstract (arXiv)

Despite their strong performance on reasoning benchmarks, large language models (LLMs) have proven brittle when presented with counterfactual questions, suggesting weaknesses in their causal reasoning ability. While recent work has demonstrated that labeled counterfactual tasks can be useful benchmarks of LLMs' causal reasoning, producing such data at the scale required to cover the vast potential space of counterfactuals is limited. In this work, we introduce double counterfactual consistency (DCC), a lightweight inference-time method for measuring and guiding the ability of LLMs to reason causally. Without requiring labeled counterfactual data, DCC verifies a model's ability to execute two important elements of causal reasoning: causal intervention and counterfactual prediction. Using DCC, we evaluate the causal reasoning abilities of various leading LLMs across a range of reasoning tasks and interventions. Moreover, we demonstrate the effectiveness of DCC as a training-free test-time rejection sampling criterion and show that it can directly improve performance on reasoning tasks across multiple model families.