ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding
This work addresses the need for better benchmarks in abstract language understanding for NLP researchers, though it is incremental as it builds on existing evaluation methods.
The authors tackled the problem of evaluating complex analogical reasoning in large language models by introducing a crowdsourced dataset of narratives for employing proverbs in context, and found that neural language models struggle on tasks like proverb recommendation and narrative generation compared to humans.
While large language models have shown exciting progress on several NLP benchmarks, evaluating their ability for complex analogical reasoning remains under-explored. Here, we introduce a high-quality crowdsourced dataset of narratives for employing proverbs in context as a benchmark for abstract language understanding. The dataset provides fine-grained annotation of aligned spans between proverbs and narratives, and contains minimal lexical overlaps between narratives and proverbs, ensuring that models need to go beyond surface-level reasoning to succeed. We explore three tasks: (1) proverb recommendation and alignment prediction, (2) narrative generation for a given proverb and topic, and (3) identifying narratives with similar motifs. Our experiments show that neural language models struggle on these tasks compared to humans, and these tasks pose multiple learning challenges.