What does this research mean for the field?

The current generation of large language models (LLMs) cannot produce an adequate book index due to issues with excessive subheadings, navigability, and accuracy. Novelty: ClaimNovelty.CONFIRMATORY. Consensus alignment: ConsensusAlignment.CHALLENGES_CONSENSUS.

What question did this study set out to answer?

The aim is to evaluate whether current large language models can effectively index a book chapter based on criteria established in previous research.

March 16, 2026

Can the current generation of large language models (LLMs) produce an adequate book index?

Key Points

The aim is to evaluate whether current large language models can effectively index a book chapter based on criteria established in previous research.
Assessment of large language models' indexing capabilities on a book chapter.
Evaluation based on criteria of completeness, navigability, and accuracy.
Comparison with findings from a prior study on earlier LLMs.
Current generation LLMs perform better than earlier versions but still lack in indexing accuracy.
Issues remain with excessive subheadings and navigability.
Overall, LLMs fail to produce an adequate book index.

Abstract

Artificial intelligence (AI) is seen as a threat to many creative professions and book indexers are no exception. This paper supplements our previously published article by investigating the capacity of the current generation of large language models (LLMs) to index a book chapter. The previous article found that an earlier generation of LLMs performed poorly on the three criteria of completeness, navigability, and accuracy. While the current generation does not under-index as severely, it has issues with excessive subheadings and navigability, and continues to fail a standard indexing test for accuracy. LLMs still cannot produce an adequate index.

Bookmark

Can the current generation of large language models (LLMs) produce an adequate book index?

Key Points

Abstract

Cite This Study