# Domain Agnostic Real-Valued Specificity Prediction

arXiv: https://arxiv.org/abs/1811.05085 · HTML: https://mlsanity.com/paper/1811.05085/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Nov 2018.

## Built on by (most cited first, 10 of 10)

- [Sparks: Inspiration for Science Writing using Language Models](https://mlsanity.com/paper/2110.07640/) (2021)
- [ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections](https://mlsanity.com/paper/2109.03438/) (2021)
- [APPLS: Evaluating Evaluation Metrics for Plain Language Summarization](https://mlsanity.com/paper/2305.14341/) (2023)
- [Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance](https://mlsanity.com/paper/2106.08007/) (2021)
- [Can Language Models Be Specific? How?](https://mlsanity.com/paper/2210.05159/) (2022)
- [Rationale-based Opinion Summarization](https://mlsanity.com/paper/2404.00217/) (2024)
- [Granuscore: A Reference-Free Measure of Granularity for Text Analysis and Question Answering](https://mlsanity.com/paper/2605.26620/) (2026)
- [A Quantitative and Qualitative Analysis of Schizophrenia Language](https://mlsanity.com/paper/2201.10430/) (2022)
- [Lightweight Decoding Strategies for Increasing Specificity](https://mlsanity.com/paper/2110.11850/) (2021)
- [Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study](https://mlsanity.com/paper/2610.01046/) (2026)

## Abstract (arXiv)

Sentence specificity quantifies the level of detail in a sentence, characterizing the organization of information in discourse. While this information is useful for many downstream applications, specificity prediction systems predict very coarse labels (binary or ternary) and are trained on and tailored toward specific domains (e.g., news). The goal of this work is to generalize specificity prediction to domains where no labeled data is available and output more nuanced real-valued specificity ratings. We present an unsupervised domain adaptation system for sentence specificity prediction, specifically designed to output real-valued estimates from binary training labels. To calibrate the values of these predictions appropriately, we regularize the posterior distribution of the labels towards a reference distribution. We show that our framework generalizes well to three different domains with 50%~68% mean absolute error reduction than the current state-of-the-art system trained for news sentence specificity. We also demonstrate the potential of our work in improving the quality and informativeness of dialogue generation systems.