Papers by Justus Mattern
Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies have shown that large language models can cause harmful, human-like biases against various demographics. |
| Approach: | They propose a causal formulation for bias measurement in generative language models based on a list of desiderata for designing robust bias benchmarks and a bias-measuring procedure to investigate occupational gender bias. |
| Outcome: | The proposed framework is generalizable and can be extended to include other datasets. |
The Limits of Word Level Differential Privacy (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to anonymize textual data have several shortcomings . authors show that they can overcome these weaknesses and offer a formal privacy guarantee . |
| Approach: | They propose a method that circumvents most of the identified weaknesses and offers a formal privacy guarantee. |
| Outcome: | The proposed method outperforms the proposed methods in thourough experimentation and shows superior performance. |
Smaller Language Models are Better Zero-shot Machine-Generated Text Detectors (2024.eacl-short)
Copied to clipboard
| Challenge: | Using large language models to detect machine generated text is difficult for humans to distinguish between human-written and machine-generated text. |
| Approach: | They propose to use one language model to detect machine-generated text produced by another language model in a zero-shot way. |
| Outcome: | The proposed methods can detect machine-generated text without additional training/data. |
Differentially Private Language Models for Secure Data Sharing (2022.emnlp-main)
Copied to clipboard
| Challenge: | a variety of deanonymization attacks allow the re-identification of individuals from tabular data. |
| Approach: | They propose to train a language model in a differentially private manner and sample data from it . they find that the model generates fluent textual datasets with privacy guarantees . |
| Outcome: | The proposed methods outperform direct classifiers with DP-SGD in the real-world. |
Membership Inference Attacks against Language Models via Neighbourhood Comparison (2023.findings-acl)
Copied to clipboard
Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schoelkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
| Challenge: | Existing membership inference attacks aim to predict whether a data sample was present in training data of a machine learning model. |
| Approach: | They propose to compare model scores to neighbour texts to eliminate access to training data by comparing model scores with a given sample. |
| Outcome: | The proposed attacks outperform reference-based attacks with perfect knowledge of the training data distribution and outperformed reference-free attacks with imperfect knowledge. |
Measuring the Impact of (Psycho-)Linguistic and Readability Features and Their Spill Over Effects on the Prediction of Eye Movement Patterns (2022.acl-long)
Copied to clipboard
| Challenge: | Existing work to predict gaze patterns during naturalistic reading has not been conducted on general text characteristics. |
| Approach: | They propose to use two eye-tracking corpora of naturalistic reading and two language models to test their performance. |
| Outcome: | The proposed models predict eye-tracking measures during naturalistic reading and language processing. |