DEVAL: A Framework for Evaluating and Improving the Derivation Capability of Large Language Models
This addresses the need for better evaluation of reasoning in LLMs for AI researchers, though it is incremental as it builds on existing prompt engineering techniques.
The paper tackles the problem of evaluating the reasoning ability of large language models (LLMs) by defining Derivation Capability (DC) and proposing the DEVAL framework, which shows that models like GPT-4o and Claude3.5 have moderate recognition but significant drop-offs in applying derivation, and introduces Derivation Prompting (DP) to improve DC by an average of 15.2%.
Assessing the reasoning ability of Large Language Models (LLMs) over data remains an open and pressing research question. Compared with LLMs, human reasoning can derive corresponding modifications to the output based on certain kinds of changes to the input. This reasoning pattern, which relies on abstract rules that govern relationships between changes of data, has not been comprehensively described or evaluated in LLMs. In this paper, we formally define this reasoning pattern as the Derivation Relation (DR) and introduce the concept of Derivation Capability (DC), i.e. applying DR by making the corresponding modification to the output whenever the input takes certain changes. To assess DC, a systematically constructed evaluation framework named DEVAL is proposed and used to evaluate five popular LLMs and one Large Reasoning Model in seven mainstream tasks. The evaluation results show that mainstream LLMs, such as GPT-4o and Claude3.5, exhibit moderate DR recognition capabilities but reveal significant drop-offs on applying DR effectively in problem-solving scenarios. To improve this, we propose a novel prompt engineering approach called Derivation Prompting (DP). It achieves an average improvement of 15.2% in DC for all tested LLMs, outperforming commonly used prompt engineering techniques.