Natural language understanding (NLU) models often suffer from unintended dataset biases. Among bias mitigation methods, ensemble-based debiasing methods, especially product-of-experts (PoE), have stood out for their impressive empirical success. However, previous ensemble-based debiasing methods typically apply debiasing on top-level logits without directly addressing biased attention patterns. Attention serves as the main media of feature interaction and aggregation in PLMs and plays a crucial role in providing robust prediction. In this paper, we propose REsidual Attention Debiasing (READ), an end-to-end debiasing method that mitigates unintended biases from attention. Experiments on three NLU benchmarks show that READ significantly improves the OOD performance of BERT-based models, including +12.9% accuracy on HANS, +11.0% accuracy on FEVER-Symmetric, and +2.7% F1 on PAWS. Detailed analyses demonstrate the crucial role of unbiased attention in robust NLU models and that READ effectively mitigates biases in attention.
more »
« less
Challenges in Automated Debiasing for Toxic Language Detection
Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text classification datasets and models, as applied to toxic language detection. Our focus is on lexical (e.g., swear words, slurs, identity mentions) and dialectal markers (specifically African American English). Our comprehensive experiments establish that existing methods are limited in their ability to prevent biased behavior in current toxicity detectors. We then propose an automatic, dialect-aware data correction method, as a proof-of-concept. Despite the use of synthetic labels, this method reduces dialectal associations with toxicity. Overall, our findings show that debiasing a model trained on biased toxic language data is not as effective as simply relabeling the data to remove existing biases.
more »
« less
- Award ID(s):
- 1714566
- NSF-PAR ID:
- 10308662
- Date Published:
- Journal Name:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Chatbot systems have improved significantly because of the advances made in language modeling. These machine learning systems follow an end-to-end data-driven learning paradigm and are trained on large conversational datasets. Imperfections or harmful biases in the training datasets can cause the models to learn toxic behavior, and thereby expose their users to harmful responses. Prior work has focused on measuring the inherent toxicity of such chatbots, by devising queries that are more likely to produce toxic responses. In this work, we ask the question: How easy or hard is it to inject toxicity into a chatbot after deployment? We study this in a practical scenario known as Dialog-based Learning (DBL), where a chatbot is periodically trained on recent conversations with its users after deployment. A DBL setting can be exploited to poison the training dataset for each training cycle. Our attacks would allow an adversary to manipulate the degree of toxicity in a model and also enable control over what type of queries can trigger a toxic response. Our fully automated attacks only require LLM-based software agents masquerading as (malicious) users to inject high levels of toxicity. We systematically explore the vulnerability of popular chatbot pipelines to this threat. Lastly, we show that several existing toxicity mitigation strategies (designed for chatbots) can be significantly weakened by adaptive attackers.more » « less
-
more » « less
Abstract With advancements in synthetic biology, the cost and the time needed for designing and synthesizing customized gene products have been steadily decreasing. Many research laboratories in academia as well as industry routinely create genetically engineered proteins as a part of their research activities. However, manipulation of protein sequences could result in unintentional production of toxic proteins. Therefore, being able to identify the toxicity of a protein before the synthesis would reduce the risk of potential hazards. Existing methods are too specific, which limits their application. Here, we extended general function prediction methods for predicting the toxicity of proteins. Protein function prediction methods have been actively studied in the bioinformatics community and have shown significant improvement over the last decade. We have previously developed successful function prediction methods, which were shown to be among top-performing methods in the community-wide functional annotation experiment, CAFA. Based on our function prediction method, we developed a neural network model, named NNTox, which uses predicted GO terms for a target protein to further predict the possibility of the protein being toxic. We have also developed a multi-label model, which can predict the specific toxicity type of the query sequence. Together, this work analyses the relationship between GO terms and protein toxicity and builds predictor models of protein toxicity.
-
Increased social media use has contributed to the greater prevalence of abusive, rude, and offensive textual comments. Machine learning models have been developed to detect toxic comments online, yet these models tend to show biases against users with marginalized or minority identities (e.g., females and African Americans). Established research in debiasing toxicity classifiers often (1) takes a static or batch approach, assuming that all information is available and then making a one-time decision; and (2) uses a generic strategy to mitigate different biases (e.g., gender and racial biases) that assumes the biases are independent of one another. However, in real scenarios, the input typically arrives as a sequence of comments/words over time instead of all at once. Thus, decisions based on partial information must be made while additional input is arriving. Moreover, social bias is complex by nature. Each type of bias is defined within its unique context, which, consistent with intersectionality theory within the social sciences, might be correlated with the contexts of other forms of bias. In this work, we consider debiasing toxicity detection as a sequential decision-making process where different biases can be interdependent. In particular, we study debiasing toxicity detection with two aims: (1) to examine whether different biases tend to correlate with each other; and (2) to investigate how to jointly mitigate these correlated biases in an interactive manner to minimize the total amount of bias. At the core of our approach is a framework built upon theories of sequential Markov Decision Processes that seeks to maximize the prediction accuracy and minimize the bias measures tailored to individual biases. Evaluations on two benchmark datasets empirically validate the hypothesis that biases tend to be correlated and corroborate the effectiveness of the proposed sequential debiasing strategy.more » « less
-
Neural machine translation (NMT) systems exhibit limited robustness in handling source-side linguistic variations. Their performance tends to degrade when faced with even slight deviations in language usage, such as different domains or variations introduced by second-language speakers. It is intuitive to extend this observation to encompass dialectal variations as well, but the work allowing the community to evaluate MT systems on this dimension is limited. To alleviate this issue, we compile and release CODET, a contrastive dialectal benchmark encompassing 891 different variations from twelve different languages. We also quantitatively demonstrate the challenges large MT models face in effectively translating dialectal variants. All the data and code have been released.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.18653/v1/2021.eacl-main.274
