# Uncovering Latent Biases in Text: Method and Application to Peer Review

arXiv: https://arxiv.org/abs/2010.15300 · HTML: https://mlsanity.com/paper/2010.15300/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 11 of 11)

- [ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing](https://mlsanity.com/paper/2306.00622/) (2023)
- [OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews](https://mlsanity.com/paper/2412.11948/) (2024)
- [Can We Automate Scientific Reviewing?](https://mlsanity.com/paper/2102.00176/) (2021)
- [What Can Natural Language Processing Do for Peer Review?](https://mlsanity.com/paper/2405.06563/) (2024)
- [Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach](https://mlsanity.com/paper/2211.06398/) (2022)
- [Near-Optimal Reviewer Splitting in Two-Phase Paper Reviewing and Conference Experiment Design](https://mlsanity.com/paper/2108.06371/) (2021)
- [Strategyproofing Peer Assessment via Partitioning: The Price in Terms of Evaluators' Expertise](https://mlsanity.com/paper/2201.10631/) (2022)
- [Large Language Models Penetration in Scholarly Writing and Peer Review](https://mlsanity.com/paper/2502.11193/) (2025)
- [A Note on Bias to Complete](https://mlsanity.com/paper/2402.11710/) (2024)
- [Are Non-English Papers Reviewed Fairly? Language-of-Study Bias in NLP Peer Reviews](https://mlsanity.com/paper/2604.07119/) (2026)
- [Who Pays for Open Review? Visible Author Reputation and Its Effect on Ratings](https://mlsanity.com/paper/2609.11983/) (2026)

## Abstract (arXiv)

Quantifying systematic disparities in numerical quantities such as employment rates and wages between population subgroups provides compelling evidence for the existence of societal biases. However, biases in the text written for members of different subgroups (such as in recommendation letters for male and non-male candidates), though widely reported anecdotally, remain challenging to quantify. In this work, we introduce a novel framework to quantify bias in text caused by the visibility of subgroup membership indicators. We develop a nonparametric estimation and inference procedure to estimate this bias. We then formalize an identification strategy to causally link the estimated bias to the visibility of subgroup membership indicators, provided observations from time periods both before and after an identity-hiding policy change. We identify an application wherein "ground truth" bias can be inferred to evaluate our framework, instead of relying on synthetic or secondary data. Specifically, we apply our framework to quantify biases in the text of peer reviews from a reputed machine learning conference before and after the conference adopted a double-blind reviewing policy. We show evidence of biases in the review ratings that serves as "ground truth", and show that our proposed framework accurately detects these biases from the review text without having access to the review ratings.