Ioana Baldini

Hammaad Adam, Ming Ying Yang, Kenrick Cato et al.

Clinical notes are becoming an increasingly important data source for machine learning (ML) applications in healthcare. Prior research has shown that deploying ML models can perpetuate existing biases against racial minorities, as bias can be implicitly embedded in data. In this study, we investigate the level of implicit race information available to ML models and human experts and the implications of model-detectable differences in clinical notes. Our work makes three key contributions. First, we find that models can identify patient self-reported race from clinical notes even when the notes are stripped of explicit indicators of race. Second, we determine that human experts are not able to accurately predict patient race from the same redacted clinical notes. Finally, we demonstrate the potential harm of this implicit information in a simulation study, and show that models trained on these race-redacted clinical notes can still perpetuate existing biases in clinical treatment decisions.

Karan Bhanot, Ioana Baldini, Dennis Wei et al.

This paper evaluates synthetically generated healthcare data for biases and investigates the effect of fairness mitigation techniques on utility-fairness. Privacy laws limit access to health data such as Electronic Medical Records (EMRs) to preserve patient privacy. Albeit essential, these laws hinder research reproducibility. Synthetic data is a viable solution that can enable access to data similar to real healthcare data without privacy risks. Healthcare datasets may have biases in which certain protected groups might experience worse outcomes than others. With the real data having biases, the fairness of synthetically generated health data comes into question. In this paper, we evaluate the fairness of models generated on two healthcare datasets for gender and race biases. We generate synthetic versions of the dataset using a Generative Adversarial Network called HealthGAN, and compare the real and synthetic model's balanced accuracy and fairness scores. We find that synthetic data has different fairness properties compared to real data and fairness mitigation techniques perform differently, highlighting that synthetic data is not bias free.

Manish Nagireddy, Lamogha Chiazor, Moninder Singh et al.

Current datasets for unwanted social bias auditing are limited to studying protected demographic features such as race and gender. In this work, we introduce a comprehensive benchmark that is meant to capture the amplification of social bias, via stigmas, in generative language models. Taking inspiration from social science research, we start with a documented list of 93 US-centric stigmas and curate a question-answering (QA) dataset which involves simple social situations. Our benchmark, SocialStigmaQA, contains roughly 10K prompts, with a variety of prompt styles, carefully constructed to systematically test for both social bias and model robustness. We present results for SocialStigmaQA with two open source generative language models and we find that the proportion of socially biased output ranges from 45% to 59% across a variety of decoding strategies and prompting styles. We demonstrate that the deliberate design of the templates in our benchmark (e.g., adding biasing text to the prompt or using different verbs that change the answer that indicates bias) impacts the model tendencies to generate socially biased output. Additionally, through manual evaluation, we discover problematic patterns in the generated chain-of-thought output that range from subtle bias to lack of reasoning. Warning: This paper contains examples of text which are toxic, biased, and potentially harmful.

Abdelrahman Zayed, Goncalo Mordido, Ioana Baldini et al.

The widespread use of large language models has brought up essential questions about the potential biases these models might learn. This led to the development of several metrics aimed at evaluating and mitigating these biases. In this paper, we first demonstrate that prompt-based fairness metrics exhibit poor agreement, as measured by correlation, raising important questions about the reliability of fairness assessment using prompts. Then, we outline six relevant reasons why such a low correlation is observed across existing metrics. Based on these insights, we propose a method called Correlated Fairness Output (CAIRO) to enhance the correlation between fairness metrics. CAIRO augments the original prompts of a given fairness metric by using several pre-trained language models and then selects the combination of the augmented prompts that achieves the highest correlation across metrics. We show a significant improvement in Pearson correlation from 0.3 and 0.18 to 0.90 and 0.98 across metrics for gender and religion biases, respectively. Our code is available at https://github.com/chandar-lab/CAIRO.

Ioana Baldini, Chhavi Yadav, Manish Nagireddy et al.

Bias auditing of language models (LMs) has received considerable attention as LMs are becoming widespread. As such, several benchmarks for bias auditing have been proposed. At the same time, the rapid evolution of LMs can make these benchmarks irrelevant in no time. Bias auditing is further complicated by LM brittleness: when a presumably biased outcome is observed, is it due to model bias or model brittleness? We propose enlisting the models themselves to help construct bias auditing datasets that remain challenging, and introduce bias measures that distinguish between different types of model errors. First, we extend an existing bias benchmark for NLI (BBNLI) using a combination of LM-generated lexical variations, adversarial filtering, and human validation. We demonstrate that the newly created dataset BBNLI-next is more challenging than BBNLI: on average, BBNLI-next reduces the accuracy of state-of-the-art NLI models from 95.3%, as observed by BBNLI, to a strikingly low 57.5%. Second, we employ BBNLI-next to showcase the interplay between robustness and bias: we point out shortcomings in current bias scores and propose bias measures that take into account both bias and model brittleness. Third, despite the fact that BBNLI-next was designed with non-generative models in mind, we show that the new dataset is also able to uncover bias in state-of-the-art open-source generative LMs. Note: All datasets included in this work are in English and they address US-centered social biases. In the spirit of efficient NLP research, no model training or fine-tuning was performed to conduct this research. Warning: This paper contains offensive text examples.

Brooklyn Sheppard, Anna Richter, Allison Cohen et al.

Using novel approaches to dataset development, the Biasly dataset captures the nuance and subtlety of misogyny in ways that are unique within the literature. Built in collaboration with multi-disciplinary experts and annotators themselves, the dataset contains annotations of movie subtitles, capturing colloquial expressions of misogyny in North American film. The dataset can be used for a range of NLP tasks, including classification, severity score regression, and text generation for rewrites. In this paper, we discuss the methodology used, analyze the annotations obtained, and provide baselines using common NLP algorithms in the context of misogyny detection and mitigation. We hope this work will promote AI for social good in NLP for bias detection, explanation, and removal.

Abdelrahman Zayed, Goncalo Mordido, Samira Shabanian et al.

The increasing size of large language models (LLMs) has introduced challenges in their training and inference. Removing model components is perceived as a solution to tackle the large model sizes, however, existing pruning methods solely focus on performance, without considering an essential aspect for the responsible use of LLMs: model fairness. It is crucial to address the fairness of LLMs towards diverse groups, such as women, Black people, LGBTQ+, Jewish communities, among others, as they are being deployed and available to a wide audience. In this work, first, we investigate how attention heads impact fairness and performance in pre-trained transformer-based language models. We then propose a novel method to prune the attention heads that negatively impact fairness while retaining the heads critical for performance, i.e. language modeling capabilities. Our approach is practical in terms of time and resources, as it does not require fine-tuning the final pruned, and fairer, model. Our findings demonstrate a reduction in gender bias by 19%, 19.5%, 39.5%, 34.7%, 23%, and 8% for DistilGPT-2, GPT-2, GPT-Neo of two different sizes, GPT-J, and Llama 2 models, respectively, in comparison to the biased model, with only a slight decrease in performance.

Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor et al. · ibm-research

Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy a library of detectors: compact and easy-to-build classification models that provide labels for various harms. In addition to the detectors themselves, we discuss a wide range of uses for these detector models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent challenges in their development and discuss future work aimed at making the detectors more reliable and broadening their scope.

Swapnaja Achintalwar, Ioana Baldini, Djallel Bouneffouf et al. · ibm-research

The alignment of large language models is usually done by model providers to add or control behaviors that are common or universally understood across use cases and contexts. In contrast, in this article, we present an approach and architecture that empowers application developers to tune a model to their particular values, social norms, laws and other regulations, and orchestrate between potentially conflicting requirements in context. We lay out three main components of such an Alignment Studio architecture: Framers, Instructors, and Auditors that work in concert to control the behavior of a language model. We illustrate this approach with a running example of aligning a company's internal-facing enterprise chatbot to its business conduct guidelines.

Kofi Arhin, Ioana Baldini, Dennis Wei et al.

The use of machine learning (ML)-based language models (LMs) to monitor content online is on the rise. For toxic text identification, task-specific fine-tuning of these models are performed using datasets labeled by annotators who provide ground-truth labels in an effort to distinguish between offensive and normal content. These projects have led to the development, improvement, and expansion of large datasets over time, and have contributed immensely to research on natural language. Despite the achievements, existing evidence suggests that ML models built on these datasets do not always result in desirable outcomes. Therefore, using a design science research (DSR) approach, this study examines selected toxic text datasets with the goal of shedding light on some of the inherent issues and contributing to discussions on navigating these challenges for existing and future projects. To achieve the goal of the study, we re-annotate samples from three toxic text datasets and find that a multi-label approach to annotating toxic text samples can help to improve dataset quality. While this approach may not improve the traditional metric of inter-annotator agreement, it may better capture dependence on context and diversity in annotators. We discuss the implications of these results for both theory and practice.

Ioana Baldini, Dennis Wei, Karthikeyan Natesan Ramamurthy et al.

The popularity of pretrained language models in natural language processing systems calls for a careful evaluation of such models in down-stream tasks, which have a higher potential for societal impact. The evaluation of such systems usually focuses on accuracy measures. Our findings in this paper call for attention to be paid to fairness measures as well. Through the analysis of more than a dozen pretrained language models of varying sizes on two toxic text classification tasks (English), we demonstrate that focusing on accuracy measures alone can lead to models with wide variation in fairness characteristics. Specifically, we observe that fairness can vary even more than accuracy with increasing training data size and different random initializations. At the same time, we find that little of the fairness variation is explained by model size, despite claims in the literature. To improve model fairness without retraining, we show that two post-processing methods developed for structured, tabular data can be successfully applied to a range of pretrained language models. Warning: This paper contains samples of offensive text.

Diego Garcia-Olano, Yasumasa Onoe, Ioana Baldini et al.

Pre-trained language models induce dense entity representations that offer strong performance on entity-centric NLP tasks, but such representations are not immediately interpretable. This can be a barrier to model uptake in important domains such as biomedicine. There has been recent work on general interpretable representation learning (Onoe and Durrett, 2020), but these domain-agnostic representations do not readily transfer to the important domain of biomedicine. In this paper, we create a new entity type system and training set from a large corpus of biomedical texts by mapping entities to concepts in a medical ontology, and from these to Wikipedia pages whose categories are our types. From this mapping we derive Biomedical Interpretable Entity Representations(BIERs), in which dimensions correspond to fine-grained entity types, and values are predicted probabilities that a given entity is of the corresponding type. We propose a novel method that exploits BIER's final sparse and intermediate dense representations to facilitate model and entity type debugging. We show that BIERs achieve strong performance in biomedical tasks including named entity disambiguation and entity label classification, and we provide error analysis to highlight the utility of their interpretability, particularly in low-supervision settings. Finally, we provide our induced 68K biomedical type system, the corresponding 37 million triples of derived data used to train BIER models and our best performing model.

Shivashankar Subramanian, Ioana Baldini, Sushma Ravichandran et al.

More than 200 generic drugs approved by the U.S. Food and Drug Administration for non-cancer indications have shown promise for treating cancer. Due to their long history of safe patient use, low cost, and widespread availability, repurposing of generic drugs represents a major opportunity to rapidly improve outcomes for cancer patients and reduce healthcare costs worldwide. Evidence on the efficacy of non-cancer generic drugs being tested for cancer exists in scientific publications, but trying to manually identify and extract such evidence is intractable. In this paper, we introduce a system to automate this evidence extraction from PubMed abstracts. Our primary contribution is to define the natural language processing pipeline required to obtain such evidence, comprising the following modules: querying, filtering, cancer type entity extraction, therapeutic association classification, and study type classification. Using the subject matter expertise on our team, we create our own datasets for these specialized domain-specific tasks. We obtain promising performance in each of the modules by utilizing modern language modeling techniques and plan to treat them as baseline approaches for future improvement of individual components.

Yaoli Mao, Dakuo Wang, Michael Muller et al.

In recent years there has been an increasing trend in which data scientists and domain experts work together to tackle complex scientific questions. However, such collaborations often face challenges. In this paper, we aim to decipher this collaboration complexity through a semi-structured interview study with 22 interviewees from teams of bio-medical scientists collaborating with data scientists. In the analysis, we adopt the Olsons' four-dimensions framework proposed in Distance Matters to code interview transcripts. Our findings suggest that besides the glitches in the collaboration readiness, technology readiness, and coupling of work dimensions, the tensions that exist in the common ground building process influence the collaboration outcomes, and then persist in the actual collaboration process. In contrast to prior works' general account of building a high level of common ground, the breakdowns of content common ground together with the strengthen of process common ground in this process is more beneficial for scientific discovery. We discuss why that is and what the design suggestions are, and conclude the paper with future directions and limitations.

Evan Patterson, Ioana Baldini, Aleksandra Mojsilovic et al.

Your computer is continuously executing programs, but does it really understand them? Not in any meaningful sense. That burden falls upon human knowledge workers, who are increasingly asked to write and understand code. They deserve to have intelligent tools that reveal the connections between code and its subject matter. Towards this prospect, we develop an AI system that forms semantic representations of computer programs, using techniques from knowledge representation and program analysis. To create the representations, we introduce an algorithm for enriching dataflow graphs with semantic information. The semantic enrichment algorithm is undergirded by a new ontology language for modeling computer programs and a new ontology about data science, written in this language. Throughout the paper, we focus on code written by data scientists and we locate our work within a larger movement towards collaborative, open, and reproducible science.