# Expect the Unexpected? Testing the Surprisal of Salient Entities

arXiv: https://arxiv.org/abs/2604.10724 · HTML: https://mlsanity.com/paper/2604.10724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 39 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Revisiting the Uniform Information Density Hypothesis](https://mlsanity.com/paper/2109.11635/) (2021)
- [SCORES: Shape Composition with Recursive Substructure Priors](https://mlsanity.com/paper/1809.05398/) (2018)
- [OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres](https://mlsanity.com/paper/2106.00933/) (2021)
- [A Cross-Linguistic Pressure for Uniform Information Density in Word Order](https://mlsanity.com/paper/2306.03734/) (2023)
- [Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse](https://mlsanity.com/paper/2410.16062/) (2024)
- [Disambiguatory Signals are Stronger in Word-initial Positions](https://mlsanity.com/paper/2102.02183/) (2021)
- [WikiGUM: Exhaustive Entity Linking for Wikification in 12 Genres](https://mlsanity.com/paper/2109.07449/) (2021)
- [GUM-SAGE: A Novel Dataset and Approach for Graded Entity Salience Prediction](https://mlsanity.com/paper/2504.10792/) (2025)
- [GDTB: Genre Diverse Data for English Shallow Discourse Parsing across Modalities, Text Types, and Domains](https://mlsanity.com/paper/2411.00491/) (2024)
- [Is Information Density Uniform when Utterances are Grounded on Perception and Discourse?](https://mlsanity.com/paper/2602.14653/) (2026)
- [Not Worth Mentioning? A Pilot Study on Salient Proposition Annotation](https://mlsanity.com/paper/2603.27358/) (2026)

## Abstract (arXiv)

Previous work examining the Uniform Information Density (UID) hypothesis has shown that while information as measured by surprisal metrics is distributed more or less evenly across documents overall, local discrepancies can arise due to functional pressures corresponding to syntactic and discourse structural constraints. However, work thus far has largely disregarded the relative salience of discourse participants. We fill this gap by studying how overall salience of entities in discourse relates to surprisal using 70K manually annotated mentions across 16 genres of English and a novel minimal-pair prompting method. Our results show that globally salient entities exhibit significantly higher surprisal than non-salient ones, even controlling for position, length, and nesting confounds. Moreover, salient entities systematically reduce surprisal for surrounding content when used as prompts, enhancing document-level predictability. This effect varies by genre, appearing strongest in topic-coherent texts and weakest in conversational contexts. Our findings refine the UID competing pressures framework by identifying global entity salience as a mechanism shaping information distribution in discourse.