We introduce ModeLing, a novel benchmark of Linguistics Olympiad-style puzzles which tests few-shot reasoning in AI systems. Solving these puzzles necessitates inferring aspects of a language’s grammatical structure from a small number of examples. Such puzzles provide a natural testbed for language models, as they require compositional generalization and few-shot inductive reasoning. Consisting solely of new puzzles written specifically for this work, ModeLing has no risk of appearing in the training data of existing AI systems: this ameliorates the risk of data leakage, a potential confounder for many prior evaluations of reasoning. Evaluating several large open source language models and GPT on our benchmark, we observe non-negligible accuracy, demonstrating few-shot emergent reasoning ability which cannot merely be attributed to shallow memorization. However, imperfect model performance suggests that ModeLing can be used to measure further progress in linguistic reasoning.

Large language models (LLMs) perform well on (at least) some evaluations of both few-shot multilingual adaptation and reasoning. However, evaluating the intersection of these two skills—multilingual few-shot reasoning—is difficult: even relatively low-resource languages can be found in large training corpora, raising the concern that when we intend to evaluate a model’s ability to generalize to a new language, that language may have in fact been present during the model’s training. If such language contamination has occurred, apparent cases of few-shot reasoning could actually be due to memorization. Towards understanding the capability of models to perform multilingual few-shot reasoning, we propose modeLing, a benchmark of Rosetta stone puzzles. This type of puzzle, originating from competitions called Linguistics Olympiads, contain a small number of sentences in a target language not previously known to the solver. Each sentence is translated to the solver’s language such that the provided sentence pairs uniquely specify a single most reasonable underlying set of rules; solving requires applying these rules to translate new expressions (Figure 1). modeLing languages are chosen to be extremely low-resource such that the risk of training data contamination is low, and unlike prior datasets, it consists entirely of problems written specifically for this work, as a further measure against data leakage. Empirically, we find evidence that popular LLMs do not have data leakage on our benchmark.

Existing table question answering datasets contain abundant factual questions that primarily evaluate a QA system’s comprehension of query and tabular data. However, restricted by their short-form answers, these datasets fail to include question–answer interactions that represent more advanced and naturally occurring information needs: questions that ask for reasoning and integration of information pieces retrieved from a structured knowledge source. To complement the existing datasets and to reveal the challenging nature of the table-based question answering task, we introduce FeTaQA, a new dataset with 10K Wikipedia-based table, question, free-form answer, supporting table cells pairs. FeTaQA is collected from noteworthy descriptions of Wikipedia tables that contain information people tend to seek; generation of these descriptions requires advanced processing that humans perform on a daily basis: Understand the question and table, retrieve, integrate, infer, and conduct text planning and surface realization to generate an answer. We provide two benchmark methods for the proposed task: a pipeline method based on semantic parsing-based QA systems and an end-to-end method based on large pretrained text generation models, and show that FeTaQA poses a challenge for both methods.