Mining Causality: AI-Assisted Search for Instrumental Variables

• URL: http://arxiv.org/abs/2409.14202v2
• Date: Mon, 11 Nov 2024 04:41:32 GMT
• Title: Mining Causality: AI-Assisted Search for Instrumental Variables
• Authors: Sukjin Han,
• Abstract summary: We propose using large language models to search for new IVs through narratives and counterfactual reasoning. We argue that multi-step and role-playing prompting strategies are effective for the endogenous decision-making processes of economic agents.
• Score: 0.0
• License:
• Abstract: The instrumental variables (IVs) method is a leading empirical strategy for causal inference. Finding IVs is a heuristic and creative process, and justifying its validity--especially exclusion restrictions--is largely rhetorical. We propose using large language models (LLMs) to search for new IVs through narratives and counterfactual reasoning, similar to how a human researcher would. The stark difference, however, is that LLMs can dramatically accelerate this process and explore an extremely large search space. We demonstrate how to construct prompts to search for potentially valid IVs. We contend that multi-step and role-playing prompting strategies are effective for simulating the endogenous decision-making processes of economic agents and for navigating language models through the realm of real-world scenarios. We apply our method to three well-known examples in economics: returns to schooling, supply and demand, and peer effects. We then extend our strategy to finding (i) control variables in regression and difference-in-differences and (ii) running variables in regression discontinuity designs.

Related papers

• Likelihood as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
  We show that likelihoods serve as an effective gauge for language model performance. We propose two methods that use question likelihood as a gauge for selecting and constructing prompts that lead to better performance.
  arXiv  Detail & Related papers  (2024-11-12T13:14:09Z)
• Large Legislative Models: Towards Efficient AI Policymaking in Economic Simulations [4.153442346657272]
  AI policymaking holds the potential to surpass human performance through the ability to process data quickly at scale. Existing RL-based methods exhibit sample inefficiency, and are further limited by an inability to flexibly incorporate nuanced information into their decision-making processes. We propose a novel method in which we instead utilize pre-trained Large Language Models (LLMs), as sample-efficient policymakers.
  arXiv  Detail & Related papers  (2024-10-10T20:04:58Z)
• Using LLMs for Explaining Sets of Counterfactual Examples to Final Users [0.0]
  In automated decision-making scenarios, causal inference methods can analyze the underlying data-generation process. Counterfactual examples explore hypothetical scenarios where a minimal number of factors are altered. We propose a novel multi-step pipeline that uses counterfactuals to generate natural language explanations of actions that will lead to a change in outcome.
  arXiv  Detail & Related papers  (2024-08-27T15:13:06Z)
• Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition [52.522244807811894]
  We propose a novel multimodal Transformer framework using prompt learning to address the issue of missing modalities. Our method introduces three types of prompts: generative prompts, missing-signal prompts, and missing-type prompts. Through prompt learning, we achieve a substantial reduction in the number of trainable parameters.
  arXiv  Detail & Related papers  (2024-07-07T13:55:56Z)
• Evaluating Interventional Reasoning Capabilities of Large Language Models [58.52919374786108]
  Large language models (LLMs) can estimate causal effects under interventions on different parts of a system. We conduct empirical analyses to evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention. We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types, and enable a study of intervention-based reasoning.
  arXiv  Detail & Related papers  (2024-04-08T14:15:56Z)
• Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs [22.619903994607792]
  We explore a new way for user targeting, where non-expert marketers could select their target users solely given demands in natural language form. We propose ARALLM consisting of two modules: Analogical Reasoning based Prompting and Reasoning-Augmented Multi-Task Model Distillation.
  arXiv  Detail & Related papers  (2024-01-09T02:25:23Z)
• How FaR Are Large Language Models From Agents with Theory-of-Mind? [69.41586417697732]
  We propose a new evaluation paradigm for large language models (LLMs): Thinking for Doing (T4D) T4D requires models to connect inferences about others' mental states to actions in social scenarios. We introduce a zero-shot prompting framework, Foresee and Reflect (FaR), which provides a reasoning structure that encourages LLMs to anticipate future challenges.
  arXiv  Detail & Related papers  (2023-10-04T06:47:58Z)
• Endogenous Macrodynamics in Algorithmic Recourse [52.87956177581998]
  Existing work on Counterfactual Explanations (CE) and Algorithmic Recourse (AR) has largely focused on single individuals in a static environment. We show that many of the existing methodologies can be collectively described by a generalized framework. We then argue that the existing framework does not account for a hidden external cost of recourse, that only reveals itself when studying the endogenous dynamics of recourse at the group level.
  arXiv  Detail & Related papers  (2023-08-16T07:36:58Z)
• Instrumental Variables in Causal Inference and Machine Learning: A Survey [26.678154268037595]
  Causal inference is a process of using assumptions to draw conclusions about the causal relationships between variables based on data. A growing literature in both causal inference and machine learning proposes to use Instrumental Variables (IV) This paper serves as the first effort to systematically and comprehensively introduce and discuss the IV methods and their applications in both causal inference and machine learning.
  arXiv  Detail & Related papers  (2022-12-12T08:59:04Z)
• Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency [61.03922379081648]
  We propose an off-policy sample efficient approach that requires no adversarial training or min-max optimization. Our empirical results show that D2-Imitation is effective in achieving good sample efficiency, outperforming several off-policy extension approaches of adversarial imitation.
  arXiv  Detail & Related papers  (2021-12-11T19:36:19Z)

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.