# Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Models

arXiv: https://arxiv.org/abs/2602.10282 · HTML: https://mlsanity.com/paper/2602.10282/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [D'ya like DAGs? A Survey on Structure Learning and Causal Discovery](https://mlsanity.com/paper/2103.02582/) (2021)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (2023)
- [CLadder: Assessing Causal Reasoning in Language Models](https://mlsanity.com/paper/2312.04350/) (2023)
- [Robust agents learn causal world models](https://mlsanity.com/paper/2402.10877/) (2024)
- [Can large language models build causal graphs?](https://mlsanity.com/paper/2303.05279/) (2023)
- [Causal Discovery with Language Models as Imperfect Experts](https://mlsanity.com/paper/2307.02390/) (2023)
- [Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI](https://mlsanity.com/paper/2402.00809/) (2024)
- [Understanding Causality with Large Language Models: Feasibility and Opportunities](https://mlsanity.com/paper/2304.05524/) (2023)
- [DISCO: Distilling Counterfactuals with Large Language Models](https://mlsanity.com/paper/2212.10534/) (2022)
- [Towards Causal Foundation Model: on Duality between Causal Inference and Attention](https://mlsanity.com/paper/2310.00809/) (2023)
- [Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization](https://mlsanity.com/paper/2505.15918/) (2025)
- [Data Augmentations for Improved (Large) Language Model Generalization](https://mlsanity.com/paper/2310.12803/) (2023)
- [bnRep: A repository of Bayesian networks from the academic literature](https://mlsanity.com/paper/2409.19158/) (2024)
- [Measuring Determinism in Large Language Models for Software Code Review](https://mlsanity.com/paper/2502.20747/) (2025)
- [Model-Preserving Sensitivity Analysis for Families of Gaussian Distributions](https://mlsanity.com/paper/1809.10794/) (2018)
- [Language Models as Causal Effect Generators](https://mlsanity.com/paper/2411.08019/) (2024)
- [The FEDHC Bayesian network learning algorithm](https://mlsanity.com/paper/2012.00113/) (2020)
- [Your Assumed DAG is Wrong and Here's How To Deal With It](https://mlsanity.com/paper/2502.17030/) (2025)
- [How Well Do LLMs Understand Drug Mechanisms? A Knowledge + Reasoning Evaluation Dataset](https://mlsanity.com/paper/2511.06418/) (2025)

## Built on by (most cited first, 1 of 1)

- [CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists](https://mlsanity.com/paper/2605.26029/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have shown potential in identifying qualitative causal relations, but their ability to perform quantitative causal reasoning---estimating effect sizes that parametrize functional relationships---remains underexplored in continuous domains. We introduce Linear-LLM-SCM, a plug-and-play framework for evaluating LLMs on Linear Gaussian structural causal model parametrization when a directed acyclic graph (DAG) is given. The framework decomposes a DAG into local parent-child sets and prompts an LLM to produce a regression-style structural equation per node, which is aggregated and compared against available ground-truth parameters. Our experiments with seven real-world DAGs effect ground truth illustrate limitations of LLMs as quantitative causal parameterizers. Across most models, we observe variability in coefficient estimates and sensitivity to structural perturbations. We open-sourced the framework to further encourage the community to work on studies toward the use of LLM for causal effect elicitation in safety-critical domain, e.g., healthcare.