Mining Causality: AI-Assisted Search for Instrumental Variables
- URL: http://arxiv.org/abs/2409.14202v1
- Date: Sat, 21 Sep 2024 17:19:29 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 demonstrate how to construct prompts to search for potentially valid IVs.
We apply our method to three well-known examples in economics: returns to schooling, production functions, and peer effects.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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 accelerate this process exponentially and explore an extremely large search space. We demonstrate how to construct prompts to search for potentially valid IVs. We argue that multi-step prompting is useful and role-playing prompts are suitable for mimicking the endogenous decisions of economic agents. We apply our method to three well-known examples in economics: returns to schooling, production functions, 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
- LogiDynamics: Unraveling the Dynamics of Logical Inference in Large Language Model Reasoning [49.58786377307728]
This paper adopts an exploratory approach by introducing a controlled evaluation environment for analogical reasoning.
We analyze the comparative dynamics of inductive, abductive, and deductive inference pipelines.
We investigate advanced paradigms such as hypothesis selection, verification, and refinement, revealing their potential to scale up logical inference.
arXiv Detail & Related papers (2025-02-16T15:54:53Z) - Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation [68.58373854950294]
We focus on causal reasoning and address the task of establishing causal relationships based on correlation information.
We introduce a prompting strategy for this problem that breaks the original task into fixed subquestions.
We evaluate our approach on an existing causal benchmark, Corr2Cause.
arXiv Detail & Related papers (2024-12-18T15:32:27Z) - 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) - 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.