# Uncovering Bias Paths with LLM-guided Causal Discovery: An Active Learning and Dynamic Scoring Approach

arXiv: https://arxiv.org/abs/2506.12227 · HTML: https://mlsanity.com/paper/2506.12227/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 47 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Fairness in Machine Learning: Lessons from Political Philosophy](https://mlsanity.com/paper/1712.03586/) (2017)
- [Fair Inference On Outcomes](https://mlsanity.com/paper/1705.10378/) (2017)
- [DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterization](https://mlsanity.com/paper/2209.08037/) (2022)
- [How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN](https://mlsanity.com/paper/2111.09509/) (2021)
- [Can large language models build causal graphs?](https://mlsanity.com/paper/2303.05279/) (2023)
- [Survey on Causal-based Machine Learning Fairness Notions](https://mlsanity.com/paper/2010.09553/) (2020)
- [Causal Reasoning for Algorithmic Fairness](https://mlsanity.com/paper/1805.05859/) (2018)
- [Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation](https://mlsanity.com/paper/1906.01732/) (2019)
- [Integrating Large Language Models in Causal Discovery: A Statistical Causal Approach](https://mlsanity.com/paper/2402.01454/) (2024)
- [ALCM: Autonomous LLM-Augmented Causal Discovery Framework](https://mlsanity.com/paper/2405.01744/) (2024)

## Built on by (most cited first, 3 of 3)

- [Step-by-Step Causality: Transparent Causal Discovery with Multi-Agent Tree-Query and Adversarial Confidence Estimation](https://mlsanity.com/paper/2601.10137/) (2026)
- [LMT: A Bayesian Framework for Causal Discovery from Textual Alarm Records in Manufacturing Systems](https://mlsanity.com/paper/2606.09892/) (2026)
- [When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models](https://mlsanity.com/paper/2608.30395/) (2026)

## Abstract (arXiv)

Ensuring fairness in machine learning requires understanding how sensitive attributes like race or gender causally influence outcomes. Existing causal discovery (CD) methods often struggle to recover fairness-relevant pathways in the presence of noise, confounding, or data corruption. Large language models (LLMs) offer a complementary signal by leveraging semantic priors from variable metadata. We propose a hybrid LLM-guided CD framework that extends a breadth-first search strategy with active learning and dynamic scoring. Variable pairs are prioritized for querying using a composite score combining mutual information, partial correlation, and LLM confidence, enabling more efficient and robust structure discovery. To evaluate fairness sensitivity, we introduce a semi-synthetic benchmark based on the UCI Adult dataset, embedding domain-informed bias pathways alongside noise and latent confounders. We assess how well CD methods recover both global graph structure and fairness-critical paths (e.g., sex-->education-->income). Our results demonstrate that LLM-guided methods, including our active, dynamically scored variant, outperform baselines in recovering fairness-relevant structure under noisy conditions. We analyze when LLM-driven insights complement statistical dependencies and discuss implications for fairness auditing in high-stakes domains.