Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores

Chantal Shaib, Venkata S. Govindarajan, Joe Barrow, Jiuding Sun, Alexa F. Siu, Byron C. Wallace, Ani Nenkova · Mar 1, 2024 · Citations: 0

Automatic Metrics

Open arXiv Find Implementation RSS feed

Abstract

The diversity across outputs generated by LLMs shapes perception of their quality and utility. High lexical diversity is often desirable, but there is no standard method to measure this property. Templated answer structures and ``canned'' responses across different documents are readily noticeable, but difficult to visualize across large corpora. This work aims to standardize measurement of text diversity. Specifically, we empirically investigate the convergent validity of existing scores across English texts, and we release diversity, an open-source Python package for measuring and extracting repetition in text. We also build a platform based on diversity for users to interactively explore repetition in text. We find that fast compression algorithms capture information similar to what is measured by slow-to-compute $n$-gram overlap homogeneity scores. Further, a combination of measures -- compression ratios, self-repetition of long $n$-grams, and Self-BLEU and BERTScore -- are sufficient to report, as they have low mutual correlation with each other.

HFEPX Relevance Assessment

This paper appears adjacent to HFEPX scope (human-feedback/eval), but does not show strong direct protocol evidence in metadata/abstract.

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: General
Extraction source: Persisted extraction

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.35
Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

bleubertscore

Research Brief

Deterministic synthesis

Further, a combination of measures -- compression ratios, self-repetition of long n-grams, and Self-BLEU and BERTScore -- are sufficient to report, as they have low mutual correlation with each other. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 5, 2026, 3:27 AM · Grounded in abstract + metadata only

Key Takeaways

Further, a combination of measures -- compression ratios, self-repetition of long n-grams, and Self-BLEU and BERTScore -- are sufficient to report, as they have low mutual…
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Actions

Treat this as method context, then pivot to protocol-specific HFEPX hubs.
Identify benchmark choices from full text before operationalizing conclusions.
Validate metric comparability (bleu, bertscore).

Caveats

Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
Low-signal flag detected: protocol relevance may be indirect.

Recommended Queries

human-eval protocol design pairwise preference data quality inter-rater agreement adjudication

Research Summary

Contribution Summary

Further, a combination of measures -- compression ratios, self-repetition of long n-grams, and Self-BLEU and BERTScore -- are sufficient to report, as they have low mutual correlation with each other.

Why It Matters For Eval

Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Pass: Evaluation mode is explicit

Detected: Automatic Metrics
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Gap: Benchmark or dataset anchors are present

No benchmark/dataset anchor extracted from abstract.
Pass: Metric reporting is present

Detected: bleu, bertscore

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Evaluating Cross-Modal Reasoning Ability and Problem Characteristics with Multimodal Item Response Theory Category Neighbor

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (text, tool)
When Numbers Tell Half the Story: Human-Metric Alignment in Topic Model Evaluation Category Neighbor

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.CL)
- Shared terminology (text, diversity)
Building a Strong Instruction Language Model for a Less-Resourced Language Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (tool)
ClinConsensus: A Consensus-Based Benchmark for Evaluating Chinese Medical LLMs across Difficulty Levels Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (scores)
Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (diversity)
Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (diversity)
Eval4Sim: An Evaluation Framework for Persona Simulation Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (scores)
Faster, Cheaper, More Accurate: Specialised Knowledge Tracing Models Outperform LLMs Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.CL)
- Shared terminology (scores)

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote