Charles Yu


pdf bib
Unlearning Bias in Language Models by Partitioning Gradients
Charles Yu | Sullam Jeoung | Anish Kasi | Pengfei Yu | Heng Ji
Findings of the Association for Computational Linguistics: ACL 2023

Recent research has shown that large-scale pretrained language models, specifically transformers, tend to exhibit issues relating to racism, sexism, religion bias, and toxicity in general. Unfortunately, these pretrained language models are used almost universally in downstream tasks, and natural language processing is often applied to make real-world predictions. Thus, debiasing these language models as early in development as possible is increasingly crucial for preventing unintentional harms caused by natural language systems. To this end, we propose a new technique called partitioned contrastive gradient unlearning (PCGU), a gray-box method for debiasing pretrained masked language models. PCGU aims to optimize only the weights that contribute most to a specific domain of bias, doing so by computing a first-order approximation based on the gradients of contrastive sentence pairs. Our experiments show that PCGU is both low-cost and seems particularly effective at pinpointing the sources of implicit social bias in large pretrained transformers. Although we train using PCGU in the gender-profession domain only, we find that doing so can also partially mitigate bias across other domains. All code for our implementation and experiments can be found at

pdf bib
Social-Group-Agnostic Bias Mitigation via the Stereotype Content Model
Ali Omrani | Alireza Salkhordeh Ziabari | Charles Yu | Preni Golazizian | Brendan Kennedy | Mohammad Atari | Heng Ji | Morteza Dehghani
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Existing bias mitigation methods require social-group-specific word pairs (e.g., “man” – “woman”) for each social attribute (e.g., gender), restricting the bias mitigation to only one specified social attribute. Further, this constraint renders such methods impractical and costly for mitigating bias in understudied and/or unmarked social groups. We propose that the Stereotype Content Model (SCM) — a theoretical framework developed in social psychology for understanding the content of stereotyping — can help debiasing efforts to become social-group-agnostic by capturing the underlying connection between bias and stereotypes. SCM proposes that the content of stereotypes map to two psychological dimensions of warmth and competence. Using only pairs of terms for these two dimensions (e.g., warmth: “genuine” – “fake”; competence: “smart” – “stupid”), we perform debiasing with established methods on both pre-trained word embeddings and large language models. We demonstrate that our social-group-agnostic, SCM-based debiasing technique performs comparably to group-specific debiasing on multiple bias benchmarks, but has theoretical and practical advantages over existing approaches.


pdf bib
RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios
Xinya Du | Zixuan Zhang | Sha Li | Pengfei Yu | Hongwei Wang | Tuan Lai | Xudong Lin | Ziqi Wang | Iris Liu | Ben Zhou | Haoyang Wen | Manling Li | Darryl Hannan | Jie Lei | Hyounghun Kim | Rotem Dror | Haoyu Wang | Michael Regan | Qi Zeng | Qing Lyu | Charles Yu | Carl Edwards | Xiaomeng Jin | Yizhu Jiao | Ghazaleh Kazeminejad | Zhenhailong Wang | Chris Callison-Burch | Mohit Bansal | Carl Vondrick | Jiawei Han | Dan Roth | Shih-Fu Chang | Martha Palmer | Heng Ji
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations

We introduce RESIN-11, a new schema-guided event extraction&prediction framework that can be applied to a large variety of newsworthy scenarios. The framework consists of two parts: (1) an open-domain end-to-end multimedia multilingual information extraction system with weak-supervision and zero-shot learningbased techniques. (2) schema matching and schema-guided event prediction based on our curated schema library. We build a demo website based on our dockerized system and schema library publicly available for installation ( We also include a video demonstrating the system.


pdf bib
Word Frequency Does Not Predict Grammatical Knowledge in Language Models
Charles Yu | Ryan Sie | Nicolas Tedeschi | Leon Bergen
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Neural language models learn, to varying degrees of accuracy, the grammatical properties of natural languages. In this work, we investigate whether there are systematic sources of variation in the language models’ accuracy. Focusing on subject-verb agreement and reflexive anaphora, we find that certain nouns are systematically understood better than others, an effect which is robust across grammatical tasks and different language models. Surprisingly, we find that across four orders of magnitude, corpus frequency is unrelated to a noun’s performance on grammatical tasks. Finally, we find that a novel noun’s grammatical properties can be few-shot learned from various types of training data. The results present a paradox: there should be less variation in grammatical performance than is actually observed.