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

• URL: http://arxiv.org/abs/2506.12227v1
• Date: Fri, 13 Jun 2025 21:04:03 GMT
• Title: Uncovering Bias Paths with LLM-guided Causal Discovery: An Active Learning and Dynamic Scoring Approach
• Authors: Khadija Zanna, Akane Sano,
• Abstract summary: Large Language Models (LLMs) offer a promising complement to statistical Causal Discovery (CD) approaches.<n> Ensuring fairness in machine learning requires understanding how sensitive attributes causally influence outcomes.<n>We propose a hybrid LLM-based framework for CD that extends a breadth-first search (BFS) strategy with active learning and dynamic scoring.
• Score: 1.5498930424110338
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Causal discovery (CD) plays a pivotal role in understanding the mechanisms underlying complex systems. While recent algorithms can detect spurious associations and latent confounding, many struggle to recover fairness-relevant pathways in realistic, noisy settings. Large Language Models (LLMs), with their access to broad semantic knowledge, offer a promising complement to statistical CD approaches, particularly in domains where metadata provides meaningful relational cues. Ensuring fairness in machine learning requires understanding how sensitive attributes causally influence outcomes, yet CD methods often introduce spurious or biased pathways. We propose a hybrid LLM-based framework for CD that extends a breadth-first search (BFS) strategy with active learning and dynamic scoring. Variable pairs are prioritized for LLM-based querying using a composite score based on mutual information, partial correlation, and LLM confidence, improving discovery efficiency and robustness. To evaluate fairness sensitivity, we construct a semi-synthetic benchmark from the UCI Adult dataset, embedding a domain-informed causal graph with injected noise, label corruption, and latent confounding. We assess how well CD methods recover both global structure and fairness-critical paths. Our results show that LLM-guided methods, including the proposed method, demonstrate competitive or superior performance in recovering such pathways under noisy conditions. We highlight when dynamic scoring and active querying are most beneficial and discuss implications for bias auditing in real-world datasets.

Related papers

• Dynamically Adaptive Reasoning via LLM-Guided MCTS for Efficient and Context-Aware KGQA [6.765017336265049]
  This paper proposes Dynamically Adaptive MCTS-based Reasoning (DAMR) for Knowledge Graph Question Answering (KGQA)<n>DAMR integrates symbolic search with adaptive path evaluation for efficient and context-aware KGQA.<n>Experiments on multiple KGQA benchmarks show DAMR significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-01T15:38:21Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Paths to Causality: Finding Informative Subgraphs Within Knowledge Graphs for Knowledge-Based Causal Discovery [10.573861741540853]
  We introduce a novel approach that integrates Knowledge Graphs (KGs) with Large Language Models (LLMs) to enhance knowledge-based causal discovery.<n>Our approach identifies informative metapath-based subgraphs within KGs and further refines the selection of these subgraphs using Learning-to-Rank-based models.<n>Our method outperforms most baselines by up to 44.4 points in F1 scores, evaluated across diverse LLMs and KGs.
  arXiv  Detail & Related papers  (2025-06-10T13:13:55Z)
• Learning to Explore: An In-Context Learning Approach for Pure Exploration [23.16863295063427]
  In this work, we study the active sequential hypothesis testing problem, also known as pure exploration.<n>We introduce In-Context Pure Exploration (ICPE), an in-context learning approach that uses Transformers to learn exploration strategies directly from experience.<n>ICPE combines supervised learning and reinforcement learning to identify and exploit latent structure across related tasks, without requiring prior assumptions.
  arXiv  Detail & Related papers  (2025-06-02T17:04:50Z)
• Fairness-Driven LLM-based Causal Discovery with Active Learning and Dynamic Scoring [1.5498930424110338]
  Causal discovery (CD) plays a pivotal role in numerous scientific fields by clarifying the causal relationships that underlie phenomena observed in diverse disciplines.<n>Despite significant advancements in CD algorithms, their application faces challenges due to the high computational demands and complexities of large-scale data.<n>This paper introduces a framework that leverages Large Language Models (LLMs) for CD, utilizing a metadata-based approach akin to the reasoning processes of human experts.
  arXiv  Detail & Related papers  (2025-03-21T22:58:26Z)
• Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning [61.99353167168545]
  We show that fine-tuning with LLM-generated data improves target task performance and reduces non-target task degradation.<n>This is the first work to provide an empirical explanation based on token perplexity reduction to mitigate catastrophic forgetting in LLMs after fine-tuning.
  arXiv  Detail & Related papers  (2025-01-24T08:18:56Z)
• Understanding Ranking LLMs: A Mechanistic Analysis for Information Retrieval [20.353393773305672]
  We employ a probing-based analysis to examine neuron activations in ranking LLMs.<n>Our study spans a broad range of feature categories, including lexical signals, document structure, query-document interactions, and complex semantic representations.<n>Our findings offer crucial insights for developing more transparent and reliable retrieval systems.
  arXiv  Detail & Related papers  (2024-10-24T08:20:10Z)
• Disentangled Noisy Correspondence Learning [56.06801962154915]
  Cross-modal retrieval is crucial in understanding latent correspondences across modalities. DisNCL is a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning.
  arXiv  Detail & Related papers  (2024-08-10T09:49:55Z)
• OCDB: Revisiting Causal Discovery with a Comprehensive Benchmark and Evaluation Framework [21.87740178652843]
  Causal discovery offers a promising approach to improve transparency and reliability. We propose a flexible evaluation framework with metrics for evaluating differences in causal structures and causal effects. We introduce the Open Causal Discovery Benchmark (OCDB), based on real data, to promote fair comparisons and drive optimization of algorithms.
  arXiv  Detail & Related papers  (2024-06-07T03:09:22Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
  c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations. Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
  arXiv  Detail & Related papers  (2024-02-17T11:28:08Z)
• Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
  We propose Mulan, a unified multi-modal causal structure learning method for root cause localization. We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data. We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
  arXiv  Detail & Related papers  (2024-02-04T05:50:38Z)
• Can Active Learning Preemptively Mitigate Fairness Issues? [66.84854430781097]
  dataset bias is one of the prevailing causes of unfairness in machine learning. We study whether models trained with uncertainty-based ALs are fairer in their decisions with respect to a protected class. We also explore the interaction of algorithmic fairness methods such as gradient reversal (GRAD) and BALD.
  arXiv  Detail & Related papers  (2021-04-14T14:20:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.