# Bridging Personalization and Control in Scientific Personalized Search

arXiv: https://arxiv.org/abs/2411.02790 · HTML: https://mlsanity.com/paper/2411.02790/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 61 references that are in the map.
- First posted on arXiv 5 Nov 2024.

## Builds on (most cited first, 21 of 21)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [Not All Relevance Scores are Equal: Efficient Uncertainty and Calibration Modeling for Deep Retrieval Models](https://mlsanity.com/paper/2105.04651/) (2021)
- [A Transformer-based Embedding Model for Personalized Product Search](https://mlsanity.com/paper/2005.08936/) (2020)
- [Editable User Profiles for Controllable Text Recommendation](https://mlsanity.com/paper/2304.04250/) (2023)
- [A Zero Attention Model for Personalized Product Search](https://mlsanity.com/paper/1908.11322/) (2019)
- [Calibration of Machine Reading Systems at Scale](https://mlsanity.com/paper/2203.10623/) (2022)
- [Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization](https://mlsanity.com/paper/2210.12579/) (2022)
- [PSSL: Self-supervised Learning for Personalized Search with Contrastive Sampling](https://mlsanity.com/paper/2111.12614/) (2021)
- [Personalizing Search Results Using Hierarchical RNN with Query-aware Attention](https://mlsanity.com/paper/1908.07600/) (2019)
- [A Personalized Dense Retrieval Framework for Unified Information Access](https://mlsanity.com/paper/2304.13654/) (2023)
- [Personalized Ranking in eCommerce Search](https://mlsanity.com/paper/1905.00052/) (2019)
- [Multivariate Representation Learning for Information Retrieval](https://mlsanity.com/paper/2304.14522/) (2023)
- [Learning to Rank Personalized Search Results in Professional Networks](https://mlsanity.com/paper/1605.04624/) (2016)
- [Leveraging User Behavior History for Personalized Email Search](https://mlsanity.com/paper/2102.07279/) (2021)
- [Fairness Vs. Personalization: Towards Equity in Epistemic Utility](https://mlsanity.com/paper/2309.11503/) (2023)

## Abstract (arXiv)

Personalized search is a problem where models benefit from learning user preferences from per-user historical interaction data. The inferred preferences enable personalized ranking models to improve the relevance of documents for users. However, personalization is also seen as opaque in its use of historical interactions and is not amenable to users' control. Further, personalization limits the diversity of information users are exposed to. While search results may be automatically diversified this does little to address the lack of control over personalization. In response, we introduce a model for personalized search that enables users to control personalized rankings proactively. Our model, CtrlCE, is a novel cross-encoder model augmented with an editable memory built from users' historical interactions. The editable memory allows cross-encoders to be personalized efficiently and enables users to control personalized ranking. Next, because all queries do not require personalization, we introduce a calibrated mixing model which determines when personalization is necessary. This enables users to control personalization via their editable memory only when necessary. To thoroughly evaluate CtrlCE, we demonstrate its empirical performance in four domains of science, its ability to selectively request user control in a calibration evaluation of the mixing model, and the control provided by its editable memory in a user study.