Fine Grained Evaluation of LLMs-as-Judges
This work addresses the problem of automating relevance assessment in IR for researchers and practitioners, but it is incremental as it builds on prior studies by adding passage-level evaluation.
The study investigated the effectiveness of Large Language Models (LLMs) as judges for evaluating document relevance in Information Retrieval, finding that LLMs perform best when used under human supervision.
A good deal of recent research has focused on how Large Language Models (LLMs) may be used as `judges' in place of humans to evaluate the quality of the output produced by various text / image processing systems. Within this broader context, a number of studies have investigated the specific question of how effectively LLMs can be used as relevance assessors for the standard ad hoc task in Information Retrieval (IR). We extend these studies by looking at additional questions. Most importantly, we use a Wikipedia based test collection created by the INEX initiative, and prompt LLMs to not only judge whether documents are relevant / non-relevant, but to highlight relevant passages in documents that it regards as useful. The human relevance assessors involved in creating this collection were given analogous instructions, i.e., they were asked to highlight all passages within a document that respond to the information need expressed in a query. This enables us to evaluate the quality of LLMs as judges not only at the document level, but to also quantify how often these `judges' are right for the right reasons. Our findings suggest that LLMs-as-judges work best under human supervision.