arXiv subjects

Saloni Dash

Publications and source records attributed to Saloni Dash.

13 recordsLinked to original sources

arXiv2026

Applications of Risk Science to AI Fairness Evaluation: Principles, Challenges, and Best Practices

Scholarly work which aims to describe potential societal impacts (e.g., risks) of proliferating technology (especially related to artificial intelligence or other algorithmic systems) is likely to have an impact beyond the scientific communities it was written for, given that general society itself is a primary object of study. However, it is an open question whether the current practices of AI evaluation scholarship follow the principles and best practices established by risk science, which aims to systematically generate knowledge related to understanding, assessing, communicating, managing, and governing risk. In this work, we examine this in depth by conducting a literature review of scholarly works purporting to evaluate the bias or fairness of technological systems used for tasks related to hiring and employment. Through analysis of 22 common fairness evaluation metrics and studies using them, we find that most characterize the severity of bias- or fairness-related consequences but do not follow best practices to characterize the uncertainty around either the occurrence of these consequences or severity estimates. Next, we conduct a case study of fairness evaluation for an AI-mediated resume screening task and demonstrate how principles of risk science can be incorporated into such an evaluation. Finally, we propose the AI Risk Report Card, which facilitates the reporting and communication of risk assessment results to stakeholders in positions to act based on the predicted risks. The outcomes of these activities suggest that further research at the convergence of risk science and AI evaluation can lead to advancements in AI assessments of societal impact by enabling shared frameworks to evaluate and discuss AI risks both within and outside of the scientific community.

cs.CY↗

arXiv2025

AI summaries in online search influence users' attitudes

This study examined how AI-generated summaries, which have become visually prominent in online search results, affect how users think about different issues. In a preregistered randomized controlled experiment, participants (N = 2,004) viewed mock search result pages varying in the presence (vs. absence), placement (top vs. middle), and stance (benefit-framed vs. harm-framed) of AI-generated summaries across four publicly debated topics. Compared to a no-summary control group, participants exposed to AI-generated summaries reported issue attitudes, behavioral intentions, and policy support that aligned more closely with the AI summary stance. The summaries placed at the top of the page produced stronger shifts in users' issue attitudes (but not behavioral intentions or policy support) than those placed at the middle of the page. We also observed moderating effects from issue familiarity and general trust toward AI. In addition, users perceived the AI summaries more useful when it emphasized health harms versus benefits. These findings suggest that AI-generated search summaries can significantly shape public perceptions, raising important implications for the design and regulation of AI-integrated information ecosystems.

cs.HC↗

arXiv2025

Anecdoctoring: Automated Red-Teaming Across Language and Place

Disinformation is among the top risks of generative artificial intelligence (AI) misuse. Global adoption of generative AI necessitates red-teaming evaluations (i.e., systematic adversarial probing) that are robust across diverse languages and cultures, but red-teaming datasets are commonly US- and English-centric. To address this gap, we propose "anecdoctoring", a novel red-teaming approach that automatically generates adversarial prompts across languages and cultures. We collect misinformation claims from fact-checking websites in three languages (English, Spanish, and Hindi) and two geographies (US and India). We then cluster individual claims into broader narratives and characterize the resulting clusters with knowledge graphs, with which we augment an attacker LLM. Our method produces higher attack success rates and offers interpretability benefits relative to few-shot prompting. Results underscore the need for disinformation mitigations that scale globally and are grounded in real-world adversarial misuse.

cs.CL↗

arXiv2025

Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning

Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This \textit{motivated reasoning} at a collective level can be detrimental to society when debating critical issues such as human-driven climate change or vaccine safety, and can further aggravate political polarization. Prior studies have reported that large language models (LLMs) are also susceptible to human-like cognitive biases, however, the extent to which LLMs selectively reason toward identity-congruent conclusions remains largely unexplored. Here, we investigate whether assigning 8 personas across 4 political and socio-demographic attributes induces motivated reasoning in LLMs. Testing 8 LLMs (open source and proprietary) across two reasoning tasks from human-subject studies -- veracity discernment of misinformation headlines and evaluation of numeric scientific evidence -- we find that persona-assigned LLMs have up to 9% reduced veracity discernment relative to models without personas. Political personas specifically are up to 90% more likely to correctly evaluate scientific evidence on gun control when the ground truth is congruent with their induced political identity. Prompt-based debiasing methods are largely ineffective at mitigating these effects. Taken together, our empirical findings are the first to suggest that persona-assigned LLMs exhibit human-like motivated reasoning that is hard to mitigate through conventional debiasing prompts -- raising concerns of exacerbating identity-congruent reasoning in both LLMs and humans.

cs.AI↗

arXiv2023

On Counterfactual Data Augmentation Under Confounding

Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the data generation process. In this paper, we formally analyze how confounding biases impact downstream classifiers and present a causal viewpoint to the solutions based on counterfactual data augmentation. We explore how removing confounding biases serves as a means to learn invariant features, ultimately aiding in generalization beyond the observed data distribution. Additionally, we present a straightforward yet powerful algorithm for generating counterfactual images, which effectively mitigates the influence of confounding effects on downstream classifiers. Through experiments on MNIST variants and the CelebA datasets, we demonstrate how our simple augmentation method helps existing state-of-the-art methods achieve good results.

cs.LG↗

arXiv2022

Counterfactual Generation Under Confounding

A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For image classifiers, augmenting a training dataset using counterfactual examples has been empirically shown to break spurious correlations. However, the counterfactual generation task itself becomes more difficult as the level of confounding increases. Existing methods for counterfactual generation under confounding consider a fixed set of interventions (e.g., texture, rotation) and are not flexible enough to capture diverse data-generating processes. Given a causal generative process, we formally characterize the adverse effects of confounding on any downstream tasks and show that the correlation between generative factors (attributes) can be used to quantitatively measure confounding between generative factors. To minimize such correlation, we propose a counterfactual generation method that learns to modify the value of any attribute in an image and generate new images given a set of observed attributes, even when the dataset is highly confounded. These counterfactual images are then used to regularize the downstream classifier such that the learned representations are the same across various generative factors conditioned on the class label. Our method is computationally efficient, simple to implement, and works well for any number of generative factors and confounding variables. Our experimental results on both synthetic (MNIST variants) and real-world (CelebA) datasets show the usefulness of our approach.

cs.LG↗

arXiv2022

Database of Indian Social Media Influencers on Twitter

Databases of highly networked individuals have been indispensable in studying narratives and influence on social media. To support studies on Twitter in India, we present a systematically categorised database of accounts of influence on Twitter in India, identified and annotated through an iterative process of friends, networks, and self-described profile information, verified manually. We built an initial set of accounts based on the friend network of a seed set of accounts based on real-world renown in various fields, and then snowballed "friends of friends" multiple times, and rank ordered individuals based on the number of in-group connections, and overall followers. We then manually classified identified accounts under the categories of entertainment, sports, business, government, institutions, journalism, civil society accounts that have independent standing outside of social media, as well as a category of "digital first" referring to accounts that derive their primary influence from online activity. Overall, we annotated 11580 unique accounts across all categories. The database is useful studying various questions related to the role of influencers in polarisation, misinformation, extreme speech, political discourse etc.

cs.SI↗

arXiv2022

Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups. However, generating counterfactual examples for images is non-trivial due to the underlying causal structure on the various features of an image. To be meaningful, generated perturbations need to satisfy constraints implied by the causal model. We present a method for generating counterfactuals by incorporating a structural causal model (SCM) in an improved variant of Adversarially Learned Inference (ALI), that generates counterfactuals in accordance with the causal relationships between attributes of an image. Based on the generated counterfactuals, we show how to explain a pre-trained machine learning classifier, evaluate its bias, and mitigate the bias using a counterfactual regularizer. On the Morpho-MNIST dataset, our method generates counterfactuals comparable in quality to prior work on SCM-based counterfactuals (DeepSCM), while on the more complex CelebA dataset our method outperforms DeepSCM in generating high-quality valid counterfactuals. Moreover, generated counterfactuals are indistinguishable from reconstructed images in a human evaluation experiment and we subsequently use them to evaluate the fairness of a standard classifier trained on CelebA data. We show that the classifier is biased w.r.t. skin and hair color, and how counterfactual regularization can remove those biases.

cs.CV↗

arXiv2021

Insights Into Incitement: A Computational Perspective on Dangerous Speech on Twitter in India

Dangerous speech on social media platforms can be framed as blatantly inflammatory, or be couched in innuendo. It is also centrally tied to who engages it - it can be driven by openly sectarian social media accounts, or through subtle nudges by influential accounts, allowing for complex means of reinforcing vilification of marginalized groups, an increasingly significant problem in the media environment in the Global South. We identify dangerous speech by influential accounts on Twitter in India around three key events, examining both the language and networks of messaging that condones or actively promotes violence against vulnerable groups. We characterize dangerous speech users by assigning Danger Amplification Belief scores and show that dangerous users are more active on Twitter as compared to other users as well as most influential in the network, in terms of a larger following as well as volume of verified accounts. We find that dangerous users have a more polarized viewership, suggesting that their audience is more susceptible to incitement. Using a mix of network centrality measures and qualitative analysis, we find that most dangerous accounts tend to either be in mass media related occupations or allied with low-ranking, right-leaning politicians, and act as "broadcasters" in the network, where they are best positioned to spearhead the rapid dissemination of dangerous speech across the platform.

cs.SI↗

arXiv2021

Extremism & Whataboutism: A Case Study on Bangalore Riots

A common diversionary tactic used to deflect attention from contested issues is whataboutery which, when used by majoritarian groups to justify their behaviour against marginalised communities, can quickly devolve into extremism. We explore the manifestations of extreme speech in the Indian context, through a case study of violent protests and policing in the city of Bangalore, provoked by a derogatory Facebook post. Analyses of the dominant narratives on Twitter surrounding the incident reveal that, most of them employ whataboutism to deflect attention from the triggering post and serve as breeding grounds for religion-based extreme speech. We conclude by discussing how our study proposes an alternative lens of viewing extremism in the Global South.

cs.SI↗

arXiv2021

Divided We Rule: Influencer Polarization on Twitter During Political Crises in India

Influencers are key to the nature and networks of information propagation on social media. Influencers are particularly important in political discourse through their engagement with issues, and may derive their legitimacy either solely or in large part through online operation, or have an offline sphere of expertise such as entertainers, journalists etc. To quantify influencers' political engagement and polarity, we use Google's Universal Sentence Encoder (USE) to encode the tweets of 6k influencers and 26k Indian politicians during political crises in India. We then obtain aggregate vector representations of the influencers based on their tweet embeddings, which alongside retweet graphs help compute their stance and polarity with respect to these political issues. We find that influencers engage with the topics in a partisan manner, with polarized influencers being rewarded with increased retweeting and following. Moreover, we observe that specific groups of influencers are consistently polarized across all events. We conclude by discussing how our study provides insights into the political schisms of present-day India, but also offers a means to study the role of influencers in exacerbating political polarization in other contexts.

cs.SI↗

arXiv2021

Rihanna versus Bollywood: Twitter Influencers and the Indian Farmers' Protest

A tweet from popular entertainer and businesswoman, Rihanna, bringing attention to farmers' protests around Delhi set off heightened activity on Indian social media. An immediate consequence was the weighing in by Indian politicians, entertainers, media and other influencers on the issue. In this paper, we use data from Twitter and an archive of debunked misinformation stories to understand some of the patterns around influencer engagement with a political issue. We found that more followed influencers were less likely to come out in support of the tweet. We also find that the later engagement of major influencers on the side of the government's position shows suggestion's of collusion. Irrespective of their position on the issue, influencers who engaged saw a significant rise in their following after their tweets. While a number of tweets thanked Rihanna for raising awareness on the issue, she was systematically trolled on the grounds of her gender, race, nationality and religion. Finally, we observed how misinformation existing prior to the tweet set up the grounds for alternative narratives that emerged.

cs.SI↗

arXiv2019

Synthetic Event Time Series Health Data Generation

Synthetic medical data which preserves privacy while maintaining utility can be used as an alternative to real medical data, which has privacy costs and resource constraints associated with it. At present, most models focus on generating cross-sectional health data which is not necessarily representative of real data. In reality, medical data is longitudinal in nature, with a single patient having multiple health events, non-uniformly distributed throughout their lifetime. These events are influenced by patient covariates such as comorbidities, age group, gender etc. as well as external temporal effects (e.g. flu season). While there exist seminal methods to model time series data, it becomes increasingly challenging to extend these methods to medical event time series data. Due to the complexity of the real data, in which each patient visit is an event, we transform the data by using summary statistics to characterize the events for a fixed set of time intervals, to facilitate analysis and interpretability. We then train a generative adversarial network to generate synthetic data. We demonstrate this approach by generating human sleep patterns, from a publicly available dataset. We empirically evaluate the generated data and show close univariate resemblance between synthetic and real data. However, we also demonstrate how stratification by covariates is required to gain a deeper understanding of synthetic data quality.

cs.LG↗