# Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study

arXiv: https://arxiv.org/abs/2610.01046 · HTML: https://mlsanity.com/paper/2610.01046/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 13 of 13)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [Structured Uncertainty guided Clarification for LLM Agents](https://mlsanity.com/paper/2511.08798/) (2025)
- [Detecting Text Formality: A Study of Text Classification Approaches](https://mlsanity.com/paper/2204.08975/) (2022)
- [RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework](https://mlsanity.com/paper/2410.19109/) (2024)
- [Domain Agnostic Real-Valued Specificity Prediction](https://mlsanity.com/paper/1811.05085/) (2018)
- [Decentralized Multi-Agent Systems with Shared Context](https://mlsanity.com/paper/2606.10662/) (2026)
- [Multi-task Domain Adaptation for Sequence Tagging](https://mlsanity.com/paper/1608.02689/) (2016)
- [Polarity and Intensity: the Two Aspects of Sentiment Analysis](https://mlsanity.com/paper/1807.01466/) (2018)
- [DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization](https://mlsanity.com/paper/2410.15687/) (2024)
- [Predicting Specificity in Classroom Discussion](https://mlsanity.com/paper/1909.01462/) (2019)
- [Detecting AI-Generated Texts in Cross-Domains](https://mlsanity.com/paper/2410.13966/) (2024)
- [Granuscore: A Reference-Free Measure of Granularity for Text Analysis and Question Answering](https://mlsanity.com/paper/2605.26620/) (2026)

## Abstract (arXiv)

Collaboration depends on shared context, and technical documentation is one way that context persists across people and AI teammates. Specificity, the amount and exactness of detail expressed in language, shapes what information documentation captures and how precisely that information is communicated. This work audits sentence-specificity scoring artifacts on technical documentation and tests whether scores applied only after generation help choose among fixed LLM-generated revisions. Across Wikipedia and three technical-documentation corpora, the fixed general-domain predictor SpeciTeller and the pinned post-publication author-repository implementation of Ko et al.'s target-adapted predictor produce different corpus orders and same-sentence rank agreement from -0.066 to 0.510. Strict filtering and token-length adjustment change these patterns without reconciling them. In the Gemma set, SpeciTeller ranking raises direction-valid selection from 71.7% to 83.3% (+11.7 points; 95% source-case bootstrap interval +1.7 to +21.7); in the GPT-OSS-120B set, SpeciTeller ranking raises direction-valid selection from 51.7% to 56.7% (+5.0 points; 95% source-case bootstrap interval -6.7 to +16.7), and every primary single-score GPT-OSS-120B interval includes zero. These findings tie score interpretation and decision value to the predictor and candidate set.