# LCSHBench: A Multilingual, Consensus-Grounded Benchmark for Library of Congress Subject Heading Assignment

arXiv: https://arxiv.org/abs/2606.04382 · HTML: https://mlsanity.com/paper/2606.04382/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 6 of 6)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Matryoshka Representation Learning](https://mlsanity.com/paper/2205.13147/) (2022)
- [MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer](https://mlsanity.com/paper/2109.00904/) (2021)
- [DNB-AI-Project at SemEval-2025 Task 5: An LLM-Ensemble Approach for Automated Subject Indexing](https://mlsanity.com/paper/2504.21589/) (2025)
- [Your Extreme Multi-label Classifier is Secretly a Hierarchical Text Classifier for Free](https://mlsanity.com/paper/2411.13687/) (2024)
- [A Skill-Based AI Agentic Pipeline for Library of Congress Subject Indexing](https://mlsanity.com/paper/2605.03537/) (2026)

## Built on by (most cited first, 1 of 1)

- [SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking](https://mlsanity.com/paper/2609.03047/) (2026)

## Abstract (arXiv)

Automated subject cataloging assigns controlledvocabulary headings to bibliographic records, but LCSH has no standard public benchmark. We introduce LCSHBench: 22,346 books in 15 languages from the openly licensed Harvard, Columbia, and Princeton catalogs. Records enter only when at least two independent cataloging agencies assigned LCSH; we release per-catalog provenance plus union and unanimous answer views. A concordance study of 465,187 works cataloged by all three libraries shows why this design matters: libraries usually agree on the underlying topic (93.3% share a concept-level heading) but often differ in exact expression (39.4% have identical heading sets). LCSHBench therefore scores both exact and concept matches, with set and rank metrics broken down by language and heading type, across open-vocabulary generation and full-vocabulary retrieval. As a first demonstration, a low-rank fine-tune of a 300M on-device embedder improves cross-lingual retrieval and beats a 3,072-dimensional hosted embedder on development exact recall@200 (0.659 vs 0.623). The language panel shows the gain is not uniform, and held-out-test and end-to-end confirmation remain future work.