Large Language Models: An Applied Econometric Framework
- URL: http://arxiv.org/abs/2412.07031v2
- Date: Fri, 03 Jan 2025 14:19:58 GMT
- Title: Large Language Models: An Applied Econometric Framework
- Authors: Jens Ludwig, Sendhil Mullainathan, Ashesh Rambachan,
- Abstract summary: We develop an econometric framework to answer this question.
Using LLMs for prediction problems is valid under one condition: no leakage'' between the LLM's training dataset and the researcher's sample.
We find that these requirements are stringent; when they are violated, the limitations of LLMs now result in unreliable empirical estimates.
- Score: 1.348318541691744
- License:
- Abstract: How can we use the novel capacities of large language models (LLMs) in empirical research? And how can we do so while accounting for their limitations, which are themselves only poorly understood? We develop an econometric framework to answer this question that distinguishes between two types of empirical tasks. Using LLMs for prediction problems (including hypothesis generation) is valid under one condition: no ``leakage'' between the LLM's training dataset and the researcher's sample. No leakage can be ensured by using open-source LLMs with documented training data and published weights. Using LLM outputs for estimation problems to automate the measurement of some economic concept (expressed either by some text or from human subjects) requires the researcher to collect at least some validation data: without such data, the errors of the LLM's automation cannot be assessed and accounted for. As long as these steps are taken, LLM outputs can be used in empirical research with the familiar econometric guarantees we desire. Using two illustrative applications to finance and political economy, we find that these requirements are stringent; when they are violated, the limitations of LLMs now result in unreliable empirical estimates. Our results suggest the excitement around the empirical uses of LLMs is warranted -- they allow researchers to effectively use even small amounts of language data for both prediction and estimation -- but only with these safeguards in place.
Related papers
- Simulating Tabular Datasets through LLMs to Rapidly Explore Hypotheses about Real-World Entities [9.235910374587734]
This paper explores the potential to quickly prototype hypotheses through applying LLMs to estimate properties of concrete entities.
The hope is to allow sifting through hypotheses more quickly through collaboration between human and machine.
arXiv Detail & Related papers (2024-11-27T05:48:44Z) - SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts.
We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM.
We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
arXiv Detail & Related papers (2024-07-16T04:41:58Z) - Large Language Models Must Be Taught to Know What They Don't Know [97.90008709512921]
We show that fine-tuning on a small dataset of correct and incorrect answers can create an uncertainty estimate with good generalization and small computational overhead.
We also investigate the mechanisms that enable reliable uncertainty estimation, finding that many models can be used as general-purpose uncertainty estimators.
arXiv Detail & Related papers (2024-06-12T16:41:31Z) - Insights from Social Shaping Theory: The Appropriation of Large Language Models in an Undergraduate Programming Course [0.9718746651638346]
Large language models (LLMs) can generate, debug, and explain code.
Our study explores how students' social perceptions influence their own LLM usage.
arXiv Detail & Related papers (2024-06-10T16:40:14Z) - $\forall$uto$\exists$val: Autonomous Assessment of LLMs in Formal Synthesis and Interpretation Tasks [21.12437562185667]
This paper presents a new approach for scaling LLM assessment in translating formal syntax to natural language.
We use context-free grammars (CFGs) to generate out-of-distribution datasets on the fly.
We also conduct an assessment of several SOTA closed and open-source LLMs to showcase the feasibility and scalability of this paradigm.
arXiv Detail & Related papers (2024-03-27T08:08:00Z) - Characterizing Truthfulness in Large Language Model Generations with
Local Intrinsic Dimension [63.330262740414646]
We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs)
We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
arXiv Detail & Related papers (2024-02-28T04:56:21Z) - Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs [60.40396361115776]
This paper introduces a novel collaborative approach, namely SlimPLM, that detects missing knowledge in large language models (LLMs) with a slim proxy model.
We employ a proxy model which has far fewer parameters, and take its answers as answers.
Heuristic answers are then utilized to predict the knowledge required to answer the user question, as well as the known and unknown knowledge within the LLM.
arXiv Detail & Related papers (2024-02-19T11:11:08Z) - LM-Polygraph: Uncertainty Estimation for Language Models [71.21409522341482]
Uncertainty estimation (UE) methods are one path to safer, more responsible, and more effective use of large language models (LLMs)
We introduce LM-Polygraph, a framework with implementations of a battery of state-of-the-art UE methods for LLMs in text generation tasks, with unified program interfaces in Python.
It introduces an extendable benchmark for consistent evaluation of UE techniques by researchers, and a demo web application that enriches the standard chat dialog with confidence scores.
arXiv Detail & Related papers (2023-11-13T15:08:59Z) - Prevalence and prevention of large language model use in crowd work [11.554258761785512]
We show that the use of large language models (LLMs) is prevalent among crowd workers.
We show that targeted mitigation strategies can significantly reduce, but not eliminate, LLM use.
arXiv Detail & Related papers (2023-10-24T09:52:09Z) - Can Large Language Models Infer Causation from Correlation? [104.96351414570239]
We test the pure causal inference skills of large language models (LLMs)
We formulate a novel task Corr2Cause, which takes a set of correlational statements and determines the causal relationship between the variables.
We show that these models achieve almost close to random performance on the task.
arXiv Detail & Related papers (2023-06-09T12:09:15Z) - Assessing Hidden Risks of LLMs: An Empirical Study on Robustness,
Consistency, and Credibility [37.682136465784254]
We conduct over a million queries to the mainstream large language models (LLMs) including ChatGPT, LLaMA, and OPT.
We find that ChatGPT is still capable to yield the correct answer even when the input is polluted at an extreme level.
We propose a novel index associated with a dataset that roughly decides the feasibility of using such data for LLM-involved evaluation.
arXiv Detail & Related papers (2023-05-15T15:44:51Z)
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.