Likert or Not: LLM Absolute Relevance Judgments on Fine-Grained Ordinal Scales

TL;DR

This paper investigates whether large language models perform better at relevance judgments when using pointwise scoring with fine-grained ordinal scales versus traditional listwise ranking, finding that larger ordinal scales diminish the performance gap.

Contribution

The study demonstrates that increasing the granularity of ordinal relevance labels in pointwise scoring reduces the performance difference compared to listwise ranking in LLM relevance tasks.

Findings

Larger ordinal relevance scales improve pointwise scoring performance.

The gap between pointwise and listwise methods becomes statistically insignificant with sufficiently fine-grained labels.

Results are consistent across multiple LLMs and benchmark datasets.

Abstract

Large language models (LLMs) obtain state of the art zero shot relevance ranking performance on a variety of information retrieval tasks. The two most common prompts to elicit LLM relevance judgments are pointwise scoring (a.k.a. relevance generation), where the LLM sees a single query-document pair and outputs a single relevance score, and listwise ranking (a.k.a. permutation generation), where the LLM sees a query and a list of documents and outputs a permutation, sorting the documents in decreasing order of relevance. The current research community consensus is that listwise ranking yields superior performance, and significant research effort has been devoted to crafting LLM listwise ranking algorithms. The underlying hypothesis is that LLMs are better at making relative relevance judgments than absolute ones. In tension with this hypothesis, we find that the gap between pointwise scoring and listwise ranking shrinks when pointwise scoring is implemented using a sufficiently large ordinal relevance label space, becoming statistically insignificant for many LLM-benchmark dataset combinations (where ``significant'' means ``95\% confidence that listwise ranking improves NDCG@10''). Our evaluations span four LLMs, eight benchmark datasets from the BEIR and TREC-DL suites, and two proprietary datasets with relevance labels collected after the training cut-off of all LLMs evaluated.