Abstract--The ability of large language models (LLMs) to perform zero-shot classification makes them viable solutions for data annotation in rapidly evolving domains where quality labeled data is often scarce and costly to obtain. However, the large-scale deployment of LLMs can be prohibitively expensive. This paper introduces an LLM chain ensemble methodology that aligns multiple LLMs in a sequence, routing data subsets to subsequent models based on classification uncertainty. This approach leverages the strengths of individual LLMs within a broader system, allowing each model to handle data points where it exhibits the highest confidence, while forwarding more complex cases to potentially more robust models. Our results show that the chain ensemble method often exceeds the performance of the best individual model in the chain and achieves substantial cost savings, making LLM chain ensembles a practical and efficient solution for large-scale data annotation challenges.

Assessing classification confidence is critical for leveraging large language models (LLMs) in automated labeling tasks, especially in the sensitive domains presented by Computational Social Science (CSS) tasks. In this paper, we make three key contributions: (1) we propose an uncertainty quantification (UQ) performance measure tailored for data annotation tasks, (2) we compare, for the first time, five different UQ strategies across three distinct LLMs and CSS data annotation tasks, (3) we introduce a novel UQ aggregation strategy that effectively identifies low-confidence LLM annotations and disproportionately uncovers data incorrectly labeled by the LLMs. Our results demonstrate that our proposed UQ aggregation strategy improves upon existing methods andcan be used to significantly improve human-in-the-loop data annotation processes.

In their recent Nature Human Behaviour paper, "Emergent analogical reasoning in large language models," (Webb, Holyoak, and Lu, 2023) the authors argue that "large language models such as GPT-3 have acquired an emergent ability to find zero-shot solutions to a broad range of analogy problems." In this response, we provide counterexamples of the letter string analogies. In our tests, GPT-3 fails to solve even the easiest variants of the problems presented in the original paper. Zero-shot reasoning is an extraordinary claim that requires extraordinary evidence. We do not see that evidence in our experiments. To strengthen claims of humanlike reasoning such as zero-shot reasoning, it is important that the field develop approaches that rule out data memorization.

Science, technology, engineering, and math (STEM) fields play growing roles in national and international economies by driving innovation and generating high salary jobs. Yet, the US is lagging behind other highly industrialized nations in terms of STEM education and training. Furthermore, many economic forecasts predict a rising shortage of domestic STEM-trained professions in the US for years to come. One potential solution to this deficit is to decrease the rates at which students leave STEM-related fields in higher education, as currently over half of all students intending to graduate with a STEM degree eventually attrite. However, little quantitative research at scale has looked at causes of STEM attrition, let alone the use of machine learning to examine how well this phenomenon can be predicted. In this paper, we detail our efforts to model and predict dropout from STEM fields using one of the largest known datasets used for research on students at a traditional campus setting. Our results suggest that attrition from STEM fields can be accurately predicted with data that is routinely collected at universities using only information on students' first academic year. We also propose a method to model student STEM intentions for each academic term to better understand the timing of STEM attrition events. We believe these results show great promise in using machine learning to improve STEM retention in traditional and non-traditional campus settings.

Each year, roughly 30% of first-year students at US baccalaureate institutions do not return for their second year and over $9 billion is spent educating these students. Yet, little quantitative research has analyzed the causes and possible remedies for student attrition. Here, we describe initial efforts to model student dropout using the largest known dataset on higher education attrition, which tracks over 32,500 students' demographics and transcript records at one of the nation's largest public universities. Our results highlight several early indicators of student attrition and show that dropout can be accurately predicted even when predictions are based on a single term of academic transcript data. These results highlight the potential for machine learning to have an impact on student retention and success while pointing to several promising directions for future work.