# Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracy

arXiv: https://arxiv.org/abs/2512.13725 · HTML: https://mlsanity.com/paper/2512.13725/

## 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 8 of its 22 references that are in the map.
- First posted on arXiv 13 Dec 2025.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [How Does Quantization Affect Multilingual LLMs?](https://mlsanity.com/paper/2407.03211/) (2024)
- [Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning](https://mlsanity.com/paper/2501.03035/) (2025)
- [Failure Modes of LLMs for Causal Reasoning on Narratives](https://mlsanity.com/paper/2410.23884/) (2024)
- [Counterfactual Causal Inference in Natural Language with Large Language Models](https://mlsanity.com/paper/2410.06392/) (2024)
- [Interpreting the Effects of Quantization on LLMs](https://mlsanity.com/paper/2508.16785/) (2025)
- [CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models](https://mlsanity.com/paper/2412.17970/) (2024)

## Abstract (arXiv)

Causal reasoning in Large Language Models spanning association, intervention, and counterfactual inference is essential for reliable decision making in high stakes settings. As deployment shifts toward edge and resource constrained environments, quantized models such as INT8 and NF4 are becoming standard. Yet the impact of precision reduction on formal causal reasoning is poorly understood. To our knowledge, this is the first study to systematically evaluate quantization effects across all three levels of Pearls Causal Ladder. Using a 3000 sample stratified CLadder benchmark, we find that rung level accuracy in Llama 3 8B remains broadly stable under quantization, with NF4 showing less than one percent overall degradation. Interventional queries at rung 2 are the most sensitive to precision loss, whereas counterfactual reasoning at rung 3 is comparatively stable but exhibits heterogeneous weaknesses across query types such as collider bias and backdoor adjustment. Experiments on the CRASS benchmark show near identical performance across precisions, indicating that existing commonsense counterfactual datasets lack the structural sensitivity needed to reveal quantization induced reasoning drift. We further evaluate Graph Retrieval Augmented Generation using ground truth causal graphs and observe a consistent improvement in NF4 interventional accuracy of plus 1.7 percent, partially offsetting compression related degradation. These results suggest that causal reasoning is unexpectedly robust to four bit quantization, graph structured augmentation can selectively reinforce interventional reasoning, and current counterfactual benchmarks fail to capture deeper causal brittleness. This work provides an initial empirical map of compressed causal reasoning and practical guidance for deploying efficient and structurally supported causal AI systems.