paper-with-me

홈 › Papers

An Explainable AI Approach to Large Language Model Assisted Causal Model Auditing and Development

2023-12-23 · YanMing Zhang, Brette Fitzgibbon, Dino Garofolo, Akshith Kota, Eric Papenhausen, Klaus Mueller

Causal networks are widely used in many fields, including epidemiology, social science, medicine, and engineering, to model the complex relationships between variables. While it can be convenient to algorithmically infer these models directly from observational data, the resulting networks are often plagued with erroneous edges. Auditing and correcting these networks may require domain expertise frequently unavailable to the analyst. We propose the use of large language models such as ChatGPT as an auditor for causal networks. Our method presents ChatGPT with a causal network, one edge at a time, to produce insights about edge directionality, possible confounders, and mediating variables. We ask ChatGPT to reflect on various aspects of each causal link and we then produce visualizations that summarize these viewpoints for the human analyst to direct the edge, gather more data, or test further hypotheses. We envision a system where large language models, automated causal inference, and the human analyst and domain expert work hand in hand as a team to derive holistic and comprehensive causal models for any given case scenario. This paper presents first results obtained with an emerging prototype.

📄 PDF Abstract BibTeX arXiv:2312.16211

Code (0)

등록된 구현이 없습니다.

Tasks

Causal InferenceEpidemiologyLanguage ModelingLanguage ModellingLarge Language Modelmodel

Similar Papers 제목 키워드 기반

PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Representative Dataset

2026-03-24 · Sumin Yu, Juhyeon Park, Taesup Moon arxiv

We present PopResume, a population-representative resume dataset for causal fairness auditing of LLM- and VLM-based resume screening systems. Unlike existing benchmarks that rely on manually injected demographic informat…

Evian: Towards Explainable Visual Instruction-tuning Data Auditing

2026-04-22 · Zimu Jia, Mingjie Xu, Andrew Estornell, Jiaheng Wei arxiv

The efficacy of Large Vision-Language Models (LVLMs) is critically dependent on the quality of their training data, requiring a precise balance between visual fidelity and instruction-following capability. Existing datas…

Logical Fallacies

A Unified Causal Framework for Auditing Recommender Systems for Ethical Concerns

2024-09-20 · Vibhhu Sharma, Shantanu Gupta, Nil-Jana Akpinar, Zachary C. Lipton 외

As recommender systems become widely deployed in different domains, they increasingly influence their users' beliefs and preferences. Auditing recommender systems is crucial as it not only ensures the continuous improvem…

Recommendation Systems

MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection

2026-05-22 · Zhewen Tan, Yilun Yao, Huiyan Jin, Wenhan Yu 외 arxiv

Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizon task execution. However, this memory mechanism also creates a prac…

Anomaly Detection

e-CARE: a New Dataset for Exploring Explainable Causal Reasoning

2022-05-12 · ACL 2022 5 · Li Du, Xiao Ding, Kai Xiong, Ting Liu 외

Understanding causality has vital importance for various Natural Language Processing (NLP) applications. Beyond the labeled instances, conceptual explanations of the causality can provide deep understanding of the causal…

valid