# Personal Salience: Highlighting Is Social, but Individuality Lives in Selection

arXiv: https://arxiv.org/abs/2606.09024 · HTML: https://mlsanity.com/paper/2606.09024/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 8 Jun 2026.

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

- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation](https://mlsanity.com/paper/2211.02570/) (2022)
- [PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation](https://mlsanity.com/paper/1804.06604/) (2018)
- [Better Highlighting: Creating Sub-Sentence Summary Highlights](https://mlsanity.com/paper/2010.10566/) (2020)
- [One Size Does Not Fit All: The Case for Personalised Word Complexity Models](https://mlsanity.com/paper/2205.02564/) (2022)

## Built on by (most cited first, 5 of 5)

- [Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting](https://mlsanity.com/paper/2606.10398/) (2026)
- [The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience](https://mlsanity.com/paper/2606.11654/) (2026)
- [Factions Within, Uncertain Across: Within-Document Reader Sub-Groups in Social Highlighting](https://mlsanity.com/paper/2606.11613/) (2026)
- [Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict?](https://mlsanity.com/paper/2608.01704/) (2026)
- [Trait, Not State: The Durability of Reading Identity in Social Highlighting](https://mlsanity.com/paper/2606.12904/) (2026)

## Abstract (arXiv)

Social highlighters let people mark passages that matter to them. We ask how much of an individual is recoverable from these naturalistic traces, using a co-readership identity control (the same document highlighted by many users) that holds document and topic fixed and asks whether a person's own history predicts their marks better than another reader's does. We separate generic salience (structure), crowd salience (what others marked), and personal salience (the individual residual). First, highlighting is social: which sentences you mark is predicted far better by the crowd than by structure or by a personal model, and even a well-estimated crowd, an information-privileged baseline that sees others' marks on the same document, beats a frontier LLM twin built from your other-document history; the within-document personal signal is at most a whisper (own-vs-other gap +0.017 by an embedding scorer, small but significant). Second, in sharp contrast, individuality lives in selection: asked which of the already-salient passages are yours, your own history is a strong, leakage-free predictor (gap +0.14). A topic decomposition shows this is largely stable thematic preference: it shrinks ~6-8x against a topically-matched peer, and a thin residual cannot be separated from finer topic. The non-obvious part is an asymmetry: under the same scorer the individual signal is ~6-8x weaker in salience than in selection. Methodologically, naive history-conditioning evaluations leak (the target's own marks enter the profile in ~42% of pairs, inflating personal scores by up to +0.15 AP) and small crowds overstate personalization; our results are leakage-free, use a dense crowd, and a model-matched control. Highlights carry a genuine individual signature, but a thin layer over a strong shared one, surfacing far more in which salient things a person selects than in what is salient.