Traceable Latent Variable Discovery Based on Multi-Agent Collaboration

TL;DR

This paper introduces TLVD, a novel causal discovery framework that combines large language models with traditional methods to infer and validate latent variables, overcoming data limitations and semantic ambiguities in causal analysis.

Contribution

The paper presents a new framework integrating LLMs with causal discovery algorithms for latent variable inference and traceability, addressing key limitations of traditional methods.

Findings

Achieved 32.67% average improvement in accuracy

Demonstrated effectiveness on real patient and benchmark datasets

Validated the traceability of inferred latent variables

Abstract

Revealing the underlying causal mechanisms in the real world is crucial for scientific and technological progress. Despite notable advances in recent decades, the lack of high-quality data and the reliance of traditional causal discovery algorithms (TCDA) on the assumption of no latent confounders, as well as their tendency to overlook the precise semantics of latent variables, have long been major obstacles to the broader application of causal discovery. To address this issue, we propose a novel causal modeling framework, TLVD, which integrates the metadata-based reasoning capabilities of large language models (LLMs) with the data-driven modeling capabilities of TCDA for inferring latent variables and their semantics. Specifically, we first employ a data-driven approach to construct a causal graph that incorporates latent variables. Then, we employ multi-LLM collaboration for latent variable inference, modeling this process as a game with incomplete information and seeking its Bayesian Nash Equilibrium (BNE) to infer the possible specific latent variables. Finally, to validate the inferred latent variables across multiple real-world web-based data sources, we leverage LLMs for evidence exploration to ensure traceability. We comprehensively evaluate TLVD on three de-identified real patient datasets provided by a hospital and two benchmark datasets. Extensive experimental results confirm the effectiveness and reliability of TLVD, with average improvements of 32.67% in Acc, 62.21% in CAcc, and 26.72% in ECit across the five datasets.