Exploring the Limitations of Large Language Models in Compositional Relation Reasoning
This work addresses the need for better evaluation of LLMs in compositional reasoning for researchers and developers, but it is incremental as it focuses on benchmarking rather than solving the problem.
The authors tackled the problem of evaluating large language models' ability to reason about compositional relations by creating a multilingual benchmark with 1,500 test cases across six types, finding limitations in their robustness and adaptability across languages.
We present a comprehensive evaluation of large language models(LLMs)' ability to reason about composition relations through a benchmark encompassing 1,500 test cases in English, designed to cover six distinct types of composition relations: Positional, Comparative, Personal, Mathematical, Identity, and Other. Acknowledging the significance of multilingual capabilities, we expanded our assessment to include translations of these cases into Chinese, Japanese, French, and Korean. Our Multilingual Composition Relation (MCR) benchmark aims at investigating the robustness and adaptability of LLMs in handling composition relation reasoning across diverse linguistic contexts.