WikiWhy: Answering and Explaining Cause-and-Effect Questions
This addresses the challenge of assessing reasoning capabilities in LLMs for researchers by providing a diverse benchmark, though it is incremental as it builds on existing QA datasets.
The authors introduced WikiWhy, a dataset of over 9,000 cause-and-effect question-answer-rationale triples from Wikipedia to benchmark reasoning in large language models, where GPT-3 achieved only 38.7% correctness in end-to-end answering and explaining.
As large language models (LLMs) grow larger and more sophisticated, assessing their "reasoning" capabilities in natural language grows more challenging. Recent question answering (QA) benchmarks that attempt to assess reasoning are often limited by a narrow scope of covered situations and subject matters. We introduce WikiWhy, a QA dataset built around a novel auxiliary task: explaining why an answer is true in natural language. WikiWhy contains over 9,000 "why" question-answer-rationale triples, grounded on Wikipedia facts across a diverse set of topics. Each rationale is a set of supporting statements connecting the question to the answer. WikiWhy serves as a benchmark for the reasoning capabilities of LLMs because it demands rigorous explicit rationales for each answer to demonstrate the acquisition of implicit commonsense knowledge, which is unlikely to be easily memorized. GPT-3 baselines achieve only 38.7% human-evaluated correctness in the end-to-end answer & explain condition, leaving significant room for future improvements.