Massive open online courses (MOOCs) unlock the doors to free education for anyone around the globe with access to a computer and the internet. Despite this democratization of learning, the massive enrollment in these courses means it is almost impossible for one instructor to assess every student's writing assignment. As a result, peer grading, often guided by a straightforward rubric, is the method of choice. While convenient, peer grading often falls short in terms of reliability and validity. In this study, using 18 distinct settings, we explore the feasibility of leveraging large language models (LLMs) to replace peer grading in MOOCs. Specifically, we focus on two state-of-the-art LLMs: GPT-4 and GPT-3.5, across three distinct courses: Introductory Astronomy, Astrobiology, and the History and Philosophy of Astronomy. To instruct LLMs, we use three different prompts based on a variant of the zero-shot chain-of-thought (Zero-shot-CoT) prompting technique: Zero-shot-CoT combined with instructor-provided correct answers; Zero-shot-CoT in conjunction with both instructor-formulated answers and rubrics; and Zero-shot-CoT with instructor-offered correct answers and LLM-generated rubrics. Our results show that Zero-shot-CoT, when integrated with instructor-provided answers and rubrics, produces grades that are more aligned with those assigned by instructors compared to peer grading. However, the History and Philosophy of Astronomy course proves to be more challenging in terms of grading as opposed to other courses. Finally, our study reveals a promising direction for automating grading systems for MOOCs, especially in subjects with well-defined rubrics.
We propose the Data Contamination Quiz, a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifically, we frame data contamination detection as a series of multiple-choice questions. We devise a quiz format wherein three perturbed versions of each dataset instance are created. These changes only include word-level perturbations, replacing words with their contextual synonyms, ensuring both the semantic and sentence structure remain exactly the same as the original instance. Together with the original instance, these perturbed versions constitute the choices in the quiz. Given that the only distinguishing signal among these choices is the exact wording, an LLM, when tasked with identifying the original instance from the choices, opts for the original if it has memorized it in its pre-training phase--a trait intrinsic to LLMs. A dataset partition is then marked as contaminated if the LLM's performance on the quiz surpasses what random chance suggests. Our evaluation spans seven datasets and their respective splits (train and test/validation) on two state-of-the-art LLMs: GPT-4 and GPT-3.5. While lacking access to the pre-training data, our results suggest that our approach not only enhances the detection of data contamination but also provides an accurate estimation of its extent, even when the contamination signal is weak.
Data contamination, i.e., the presence of test data from downstream tasks in the training data of large language models (LLMs), is a potential major issue in understanding LLMs' effectiveness on other tasks. We propose a straightforward yet effective method for identifying data contamination within LLMs. At its core, our approach starts by identifying potential contamination in individual instances that are drawn from a small random sample; using this information, our approach then assesses if an entire dataset partition is contaminated. To estimate contamination of individual instances, we employ "guided instruction:" a prompt consisting of the dataset name, partition type, and the initial segment of a reference instance, asking the LLM to complete it. An instance is flagged as contaminated if the LLM's output either exactly or closely matches the latter segment of the reference. To understand if an entire partition is contaminated, we propose two ideas. The first idea marks a dataset partition as contaminated if the average overlap score with the reference instances (as measured by ROUGE or BLEURT) is statistically significantly better with the guided instruction vs. a general instruction that does not include the dataset and partition name. The second idea marks a dataset as contaminated if a classifier based on GPT-4 with in-context learning prompting marks multiple instances as contaminated. Our best method achieves an accuracy between 92% and 100% in detecting if an LLM is contaminated with seven datasets, containing train and test/validation partitions, when contrasted with manual evaluation by human expert. Further, our findings indicate that GPT-4 is contaminated with AG News, WNLI, and XSum datasets.
We propose a novel task-agnostic in-domain pre-training method that sits between generic pre-training and fine-tuning. Our approach selectively masks in-domain keywords, i.e., words that provide a compact representation of the target domain. We identify such keywords using KeyBERT (Grootendorst, 2020). We evaluate our approach using six different settings: three datasets combined with two distinct pre-trained language models (PLMs). Our results reveal that the fine-tuned PLMs adapted using our in-domain pre-training strategy outperform PLMs that used in-domain pre-training with random masking as well as those that followed the common pre-train-then-fine-tune paradigm. Further, the overhead of identifying in-domain keywords is reasonable, e.g., 7-15% of the pre-training time (for two epochs) for BERT Large (Devlin et al., 2019).
Domain adaptation for large neural language models (NLMs) is coupled with massive amounts of unstructured data in the pretraining phase. In this study, however, we show that pretrained NLMs learn in-domain information more effectively and faster from a compact subset of the data that focuses on the key information in the domain. We construct these compact subsets from the unstructured data using a combination of abstractive summaries and extractive keywords. In particular, we rely on BART to generate abstractive summaries, and KeyBERT to extract keywords from these summaries (or the original unstructured text directly). We evaluate our approach using six different settings: three datasets combined with two distinct NLMs. Our results reveal that the task-specific classifiers trained on top of NLMs pretrained using our method outperform methods based on traditional pretraining, i.e., random masking on the entire data, as well as methods without pretraining. Further, we show that our strategy reduces pretraining time by up to five times compared to vanilla pretraining. The code for all of our experiments is publicly available at https://github.com/shahriargolchin/compact-pretraining.