$T^5Score$: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Sets
This addresses the need for reliable evaluation methods for LLM-generated topics in multi-document analysis, which is incremental as it builds on existing evaluation practices.
The paper tackles the problem of low inter-annotator agreement in evaluating LLM-generated multi-document topic sets by introducing T^5Score, a methodology that decomposes topic quality into quantifiable aspects, resulting in a strong inter-annotator agreement score.
Using LLMs for Multi-Document Topic Extraction has recently gained popularity due to their apparent high-quality outputs, expressiveness, and ease of use. However, most existing evaluation practices are not designed for LLM-generated topics and result in low inter-annotator agreement scores, hindering the reliable use of LLMs for the task. To address this, we introduce $T^5Score$, an evaluation methodology that decomposes the quality of a topic set into quantifiable aspects, measurable through easy-to-perform annotation tasks. This framing enables a convenient, manual or automatic, evaluation procedure resulting in a strong inter-annotator agreement score. To substantiate our methodology and claims, we perform extensive experimentation on multiple datasets and report the results.