ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2310.15117
58
38
v1v2 (latest)

Causal Inference Using LLM-Guided Discovery

23 October 2023
Aniket Vashishtha
Abbavaram Gowtham Reddy
Abhinav Kumar
Saketh Bachu
Vineeth N. Balasubramanian
Amit Sharma
    CML
ArXiv (abs)PDFHTML
Abstract

At the core of causal inference lies the challenge of determining reliable causal graphs solely based on observational data. Since the well-known backdoor criterion depends on the graph, any errors in the graph can propagate downstream to effect inference. In this work, we initially show that complete graph information is not necessary for causal effect inference; the topological order over graph variables (causal order) alone suffices. Further, given a node pair, causal order is easier to elicit from domain experts compared to graph edges since determining the existence of an edge can depend extensively on other variables. Interestingly, we find that the same principle holds for Large Language Models (LLMs) such as GPT-3.5-turbo and GPT-4, motivating an automated method to obtain causal order (and hence causal effect) with LLMs acting as virtual domain experts. To this end, we employ different prompting strategies and contextual cues to propose a robust technique of obtaining causal order from LLMs. Acknowledging LLMs' limitations, we also study possible techniques to integrate LLMs with established causal discovery algorithms, including constraint-based and score-based methods, to enhance their performance. Extensive experiments demonstrate that our approach significantly improves causal ordering accuracy as compared to discovery algorithms, highlighting the potential of LLMs to enhance causal inference across diverse fields.

View on arXiv
@article{vashishtha2025_2310.15117,
  title={ Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference },
  author={ Aniket Vashishtha and Abbavaram Gowtham Reddy and Abhinav Kumar and Saketh Bachu and Vineeth N Balasubramanian and Amit Sharma },
  journal={arXiv preprint arXiv:2310.15117},
  year={ 2025 }
}
Comments on this paper