# Towards a Universal Causal Reasoner

arXiv: https://arxiv.org/abs/2605.24873 · HTML: https://mlsanity.com/paper/2605.24873/

## 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 13 of its 46 references that are in the map.
- First posted on arXiv 24 May 2026.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Reinforcement Learning via Self-Distillation](https://mlsanity.com/paper/2601.20802/) (2026)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [Olmo 3](https://mlsanity.com/paper/2512.13961/) (2025)
- [CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models](https://mlsanity.com/paper/2502.11008/) (2025)
- [Causal Evaluation of Language Models](https://mlsanity.com/paper/2405.00622/) (2024)
- [Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code](https://mlsanity.com/paper/2510.01539/) (2025)
- [Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference](https://mlsanity.com/paper/2505.13770/) (2025)
- [C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs](https://mlsanity.com/paper/2512.23430/) (2025)
- [Can Post-Training Transform LLMs into Causal Reasoners?](https://mlsanity.com/paper/2602.06337/) (2026)
- [CARE: Turning LLMs Into Causal Reasoning Expert](https://mlsanity.com/paper/2511.16016/) (2025)

## Abstract (arXiv)

Despite the importance of causal reasoning, training LLMs to reason causally remains underexplored. Existing data efforts mostly focus on benchmarking LLMs on specific aspects of causality, making them less suitable for training generalizable causal reasoners. To address this, we propose UniCo, a data generation framework that both (1) addresses 18 causal query types across Pearl's Causal Ladder and (2) translates natively symbolic examples into code and natural language forms to simulate real-world use cases where causal terms are not explicitly specified. To ensure data quality, UniCo grounds answers with exact causal inference and filters cases with reasoning shortcuts. Upon supervised finetuning with 66.6K UniCo-generated instances, Qwen3-4B, Qwen3-8B and Olmo-3-7B-Instruct achieve an average of 22.9% improvements across all 18 in-distribution query types, and 8.1% over state-of-the-art causal data generation frameworks on 7 established causal benchmarks outside the training distribution. More importantly, in real-world medical understanding, legal decision, and tabular reasoning, UniCo-trained models consistently display more faithful reasoning traces, outperforming the base models by an average of 20.2% in faithfulness metrics. These suggest that causality-centered training not only strengthens causal reasoning, but also equips LLMs with a causal mindset in general reasoning tasks.