BRAINTEASER: Lateral Thinking Puzzles for Large Language Models
This addresses the problem of evaluating complex reasoning in AI for NLP researchers, though it is incremental as it introduces a new benchmark rather than a novel method.
The authors tackled the lack of lateral thinking benchmarks for large language models by creating BRAINTEASER, a multiple-choice QA task with 1,100 puzzles, and found a significant performance gap between models and humans, especially when considering consistency across adversarial formats.
The success of language models has inspired the NLP community to attend to tasks that require implicit and complex reasoning, relying on human-like commonsense mechanisms. While such vertical thinking tasks have been relatively popular, lateral thinking puzzles have received little attention. To bridge this gap, we devise BRAINTEASER: a multiple-choice Question Answering task designed to test the model's ability to exhibit lateral thinking and defy default commonsense associations. We design a three-step procedure for creating the first lateral thinking benchmark, consisting of data collection, distractor generation, and generation of adversarial examples, leading to 1,100 puzzles with high-quality annotations. To assess the consistency of lateral reasoning by models, we enrich BRAINTEASER based on a semantic and contextual reconstruction of its questions. Our experiments with state-of-the-art instruction- and commonsense language models reveal a significant gap between human and model performance, which is further widened when consistency across adversarial formats is considered. We make all of our code and data available to stimulate work on developing and evaluating lateral thinking models.