Large Language Models (LLMs) are widely used for downstream tasks such as tabular classification, where ensuring fairness in their outputs is critical for inclusivity, equal representation, and responsible AI deployment. This study introduces a novel approach to enhancing LLM performance and fairness through the concept of a dynamic validation set, which evolves alongside the test set, replacing the traditional static validation approach. We also propose an iterative algorithm, SMITE, to select optimal in-context examples, with each example set validated against its corresponding dynamic validation set. The in-context set with the lowest total error is used as the final demonstration set. Our experiments across four different LLMs show that our proposed techniques significantly improve both predictive accuracy and fairness compared to baseline methods. To our knowledge, this is the first study to apply dynamic validation in the context of in-context learning for LLMs.

The rise of large language models (LLMs) has raised concerns about machine-generated text (MGT), including ethical and practical issues like plagiarism and misinformation. Building a robust and highly generalizable MGT detection system has become increasingly important. This work investigates the generalization capabilities of MGT detectors in three aspects: First, we construct MGTAcademic, a large-scale dataset focused on academic writing, featuring human-written texts (HWTs) and MGTs across STEM, Humanities, and Social Sciences, paired with an extensible code framework for efficient benchmarking. Second, we investigate the transferability of detectors across domains and LLMs, leveraging fine-grained datasets to reveal insights into domain transferring and implementing few-shot techniques to improve the performance by roughly 13.2%. Third, we introduce a novel attribution task where models must adapt to new classes over time without (or with very limited) access to prior training data and benchmark detectors. We implement several adapting techniques to improve the performance by roughly 10% and highlight the inherent complexity of the task. Our findings provide insights into the generalization ability of MGT detectors across diverse scenarios and lay the foundation for building robust, adaptive detection systems.

Large language models (LLMs) can now generate and recognize text in a wide range of styles and genres, including highly specialized, creative genres like poetry. But what do LLMs really know about poetry? What can they know about poetry? We develop a task to evaluate how well LLMs recognize a specific aspect of poetry, poetic form, for more than 20 forms and formal elements in the English language. Poetic form captures many different poetic features, including rhyme scheme, meter, and word or line repetition. We use this task to reflect on LLMs' current poetic capabilities, as well as the challenges and pitfalls of creating NLP benchmarks for poetry and for other creative tasks. In particular, we use this task to audit and reflect on the poems included in popular pretraining datasets. Our findings have implications for NLP researchers interested in model evaluation, digital humanities and cultural analytics scholars, and cultural heritage professionals.

Statements involving metalinguistic self-reference ("This paper has six sections.") are prevalent in many domains. Can large language models (LLMs) handle such language? In this paper, we present "I am a Strange Dataset", a new dataset for addressing this question. There are two subtasks: generation and verification. In generation, models continue statements like "The penultimate word in this sentence is" (where a correct continuation is "is"). In verification, models judge the truth of statements like "The penultimate word in this sentence is sentence." (false). We also provide minimally different metalinguistic non-self-reference examples to complement the main dataset by probing for whether models can handle metalinguistic language at all. The dataset is hand-crafted by experts and validated by non-expert annotators. We test a variety of open-source LLMs (7B to 70B parameters) as well as closed-source LLMs through APIs. All models perform close to chance across both subtasks and even on the non-self-referential metalinguistic control data, though we find some steady improvement with model scale. GPT 4 is the only model to consistently do significantly better than chance, and it is still only in the 60% range, while our untrained human annotators score well in the 89-93% range. The dataset and evaluation toolkit are available at https://github.com/TristanThrush/i-am-a-strange-dataset.

The recently released Google Gemini class of models are the first to comprehensively report results that rival the OpenAI GPT series across a wide variety of tasks. In this paper, we do an in-depth exploration of Gemini's language abilities, making two contributions. First, we provide a third-party, objective comparison of the abilities of the OpenAI GPT and Google Gemini models with reproducible code and fully transparent results. Second, we take a closer look at the results, identifying areas where one of the two model classes excels. We perform this analysis over 10 datasets testing a variety of language abilities, including reasoning, answering knowledge-based questions, solving math problems, translating between languages, generating code, and acting as instruction-following agents. From this analysis, we find that Gemini Pro achieves accuracy that is close but slightly inferior to the corresponding GPT 3.5 Turbo on all English-language tasks that we benchmarked, but find that Gemini Pro excels in translation into other languages for the languages that it supports. We further provide explanations for some of the under-performing tasks, including failures in mathematical reasoning with many digits, sensitivity to multiple-choice answer ordering, and others. We also identify areas where Gemini Pro demonstrates comparably high performance, such as handling longer and more complex reasoning chains.