Agent-based Automated Claim Matching with Instruction-following LLMs
This work addresses claim matching for automated systems, offering incremental improvements in efficiency and performance.
The paper tackles automated claim matching by proposing a two-step agent-based pipeline using instruction-following LLMs, where LLM-generated prompts outperform state-of-the-art human-generated prompts and smaller LLMs achieve similar performance to larger ones, saving computational resources.
We present a novel agent-based approach for the automated claim matching task with instruction-following LLMs. We propose a two-step pipeline that first generates prompts with LLMs, to then perform claim matching as a binary classification task with LLMs. We demonstrate that LLM-generated prompts can outperform SOTA with human-generated prompts, and that smaller LLMs can do as well as larger ones in the generation process, allowing to save computational resources. We also demonstrate the effectiveness of using different LLMs for each step of the pipeline, i.e. using an LLM for prompt generation, and another for claim matching. Our investigation into the prompt generation process in turn reveals insights into the LLMs' understanding of claim matching.