arXiv subjects

Ramaravind Kommiya Mothilal

Publications and source records attributed to Ramaravind Kommiya Mothilal.

12 recordsLinked to original sources

arXiv2026

Activating the Annotator: Operationalising Lived Experience in Data Annotation

Perspectivist NLP has established that annotator positionality shapes labels for subjective tasks, but the field still lacks methods for operationalising it. Positionality is typically operationalised as a demographic form completed at recruitment: a static attribute recorded once and treated as a covariate, on the assumption that the knowledge it indexes is active when the annotator reads an item. This paper treats that assumption as a design problem and asks whether lived experience can instead be primed by the task itself. We introduce AXLE, a pre-annotation stage in which a scenario vignette anchors a short, axis-guided conversation that is synthesised into a first-person micro-narrative and returned to the annotator before labelling begins. In a 2x2 between-subjects study (104 annotators, 30 items, 1,040 annotations) on ambiguous hate speech spanning immigration, religion and gender, elicitation was associated with higher identity resonance and higher sensitivity to harm. It also increased label entropy and lowered inter-annotator agreement: the stage appears to surface plurality rather than manufacture consensus, which distinguishes it from annotator training, whose success criterion is convergence.

cs.CL↗

arXiv2026

Evaluating Second-Order Bias of LLMs Through Epistemic Entitlement

Evaluations of social bias in LLMs largely focus on whether models generate or imply biased content. However, as LLMs are increasingly used as judges of bias, they may exhibit social biases in subtler ways in how they evaluate biased content, which current methods do not systematically capture. We call this second-order bias: social bias in an LLM's judgment about social bias, which we evaluate through a novel, philosophically grounded reasoning task. Drawing on entitlement epistemology, we conceptualize bias as misplaced foundational knowledge that shapes an agent's rational inquiry, and derive a logical reasoning task for LLMs to judge to whom a biased text is acceptable or non-acceptable. We develop two simple metrics to measure how biased LLM judges are in inferring demographics for acceptability without sufficient support, and how these inferences vary across groups targeted by biased texts. Evaluating open and closed models, we find that our task evades safety guardrails by surfacing bias in model judgment. It varies systematically across target groups, reflects implicit social maps, and shows how models are still triggered by demographic labels. Our work points to the need for LLM bias evaluation in judgment tasks and broadly, for more theoretically grounded approaches to bias evaluation in NLP. We release our code and model responses at https://github.com/uofthcdslab/second-order-bias.

cs.CL↗

arXiv2026

Argument-Based Consistency in Toxicity Explanations of LLMs

The discourse around toxicity and LLMs in NLP largely revolves around detection tasks. This work shifts the focus to evaluating LLMs' reasoning about toxicity - from their explanations that justify a stance - to enhance their trustworthiness in downstream tasks. Despite extensive research on explainability, it is not straightforward to adopt existing methods to evaluate free-form toxicity explanation due to their over-reliance on input text perturbations, among other challenges. To account for these, we propose a novel, theoretically-grounded multi-dimensional criterion, Argument-based Consistency (ArC), that measures the extent to which LLMs' free-form toxicity explanations reflect an ideal and logical argumentation process. Based on uncertainty quantification, we develop six metrics for ArC to comprehensively evaluate the (in)consistencies in LLMs' toxicity explanations. We conduct several experiments on three Llama models (of size up to 70B) and an 8B Ministral model on five diverse toxicity datasets. Our results show that while LLMs generate plausible explanations to simple prompts, their reasoning about toxicity breaks down when prompted about the nuanced relations between the complete set of reasons, the individual reasons, and their toxicity stances, resulting in inconsistent and irrelevant responses. We open-source our code (https://github.com/uofthcdslab/ArC) and LLM-generated explanations (https://huggingface.co/collections/uofthcdslab/arc) for future works.

cs.CL↗

arXiv2025

Reasoning About Reasoning: Towards Informed and Reflective Use of LLM Reasoning in HCI

Reasoning is a distinctive human-like characteristic attributed to LLMs in HCI due to their ability to simulate various human-level tasks. However, this work argues that the reasoning behavior of LLMs in HCI is often decontextualized from the underlying mechanics and subjective decisions that condition the emergence and human interpretation of this behavior. Through a systematic survey of 258 CHI papers from 2020-2025 on LLMs, we discuss how HCI hardly perceives LLM reasoning as a product of sociotechnical orchestration and often references it as an object of application. We argue that such abstraction leads to oversimplification of reasoning methodologies from NLP/ML and results in a distortion of LLMs' empirically studied capabilities and (un)known limitations. Finally, drawing on literature from both NLP/ML and HCI, as a constructive step forward, we develop reflection prompts to support HCI practitioners engage with LLM reasoning in an informed and reflective way.

cs.HC↗

arXiv2025

Talking About the Assumption in the Room

The reference to assumptions in how practitioners use or interact with machine learning (ML) systems is ubiquitous in HCI and responsible ML discourse. However, what remains unclear from prior works is the conceptualization of assumptions and how practitioners identify and handle assumptions throughout their workflows. This leads to confusion about what assumptions are and what needs to be done with them. We use the concept of an argument from Informal Logic, a branch of Philosophy, to offer a new perspective to understand and explicate the confusions surrounding assumptions. Through semi-structured interviews with 22 ML practitioners, we find what contributes most to these confusions is how independently assumptions are constructed, how reactively and reflectively they are handled, and how nebulously they are recorded. Our study brings the peripheral discussion of assumptions in ML to the center and presents recommendations for practitioners to better think about and work with assumptions.

cs.HC↗

arXiv2024

Towards a Non-Ideal Methodological Framework for Responsible ML

Though ML practitioners increasingly employ various Responsible ML (RML) strategies, their methodological approach in practice is still unclear. In particular, the constraints, assumptions, and choices of practitioners with technical duties -- such as developers, engineers, and data scientists -- are often implicit, subtle, and under-scrutinized in HCI and related fields. We interviewed 22 technically oriented ML practitioners across seven domains to understand the characteristics of their methodological approaches to RML through the lens of ideal and non-ideal theorizing of fairness. We find that practitioners' methodological approaches fall along a spectrum of idealization. While they structured their approaches through ideal theorizing, such as by abstracting RML workflow from the inquiry of applicability of ML, they did not pay deliberate attention and systematically documented their non-ideal approaches, such as diagnosing imperfect conditions. We end our paper with a discussion of a new methodological approach, inspired by elements of non-ideal theory, to structure technical practitioners' RML process and facilitate collaboration with other stakeholders.

cs.HC↗

arXiv2022

Learnings from Technological Interventions in a Low Resource Language: Enhancing Information Access in Gondi

The primary obstacle to developing technologies for low-resource languages is the lack of representative, usable data. In this paper, we report the deployment of technology-driven data collection methods for creating a corpus of more than 60,000 translations from Hindi to Gondi, a low-resource vulnerable language spoken by around 2.3 million tribal people in south and central India. During this process, we help expand information access in Gondi across 2 different dimensions (a) The creation of linguistic resources that can be used by the community, such as a dictionary, children's stories, Gondi translations from multiple sources and an Interactive Voice Response (IVR) based mass awareness platform; (b) Enabling its use in the digital domain by developing a Hindi-Gondi machine translation model, which is compressed by nearly 4 times to enable it's edge deployment on low-resource edge devices and in areas of little to no internet connectivity. We also present preliminary evaluations of utilizing the developed machine translation model to provide assistance to volunteers who are involved in collecting more data for the target language. Through these interventions, we not only created a refined and evaluated corpus of 26,240 Hindi-Gondi translations that was used for building the translation model but also engaged nearly 850 community members who can help take Gondi onto the internet.

cs.CL↗

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↗

arXiv2021

Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End

Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter provides input examples with minimal changes to alter the model's predictions. To unify these approaches, we provide an interpretation based on the actual causality framework and present two key results in terms of their use. First, we present a method to generate feature attribution explanations from a set of counterfactual examples. These feature attributions convey how important a feature is to changing the classification outcome of a model, especially on whether a subset of features is necessary and/or sufficient for that change, which attribution-based methods are unable to provide. Second, we show how counterfactual examples can be used to evaluate the goodness of an attribution-based explanation in terms of its necessity and sufficiency. As a result, we highlight the complementarity of these two approaches. Our evaluation on three benchmark datasets - Adult-Income, LendingClub, and German-Credit - confirms the complementarity. Feature attribution methods like LIME and SHAP and counterfactual explanation methods like Wachter et al. and DiCE often do not agree on feature importance rankings. In addition, by restricting the features that can be modified for generating counterfactual examples, we find that the top-k features from LIME or SHAP are often neither necessary nor sufficient explanations of a model's prediction. Finally, we present a case study of different explanation methods on a real-world hospital triage problem

cs.LG↗

arXiv2021

Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi

The primary obstacle to developing technologies for low-resource languages is the lack of usable data. In this paper, we report the adoption and deployment of 4 technology-driven methods of data collection for Gondi, a low-resource vulnerable language spoken by around 2.3 million tribal people in south and central India. In the process of data collection, we also help in its revival by expanding access to information in Gondi through the creation of linguistic resources that can be used by the community, such as a dictionary, children's stories, an app with Gondi content from multiple sources and an Interactive Voice Response (IVR) based mass awareness platform. At the end of these interventions, we collected a little less than 12,000 translated words and/or sentences and identified more than 650 community members whose help can be solicited for future translation efforts. The larger goal of the project is collecting enough data in Gondi to build and deploy viable language technologies like machine translation and speech to text systems that can help take the language onto the internet.

cs.CL↗

arXiv2020

Indian Political Twitter and Caste Discrimination -- How Representation Does Not Equal Inclusion in Lok Sabha Networks

Caste privilege persists in the form of upper caste "networks" in India made up of political, social, and economic relations that tend to actively exclude lower caste members. In this study, we examine this pernicious expression of caste in the Twitter networks of politicians from India's highest legislative body - the Lok Sabha. We find that caste has a significant relationship with the centrality, connectivity and engagement of an MP in the Lok Sabha Twitter network. The higher the caste of a Member of the Parliament (MP) the more likely they are to be important in the network, to have reciprocal connections with other MPs, and to get retweeted by an upper caste MPs.

cs.SI↗

arXiv2019

Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations

Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions. An intriguing class of explanations is through counterfactuals, hypothetical examples that show people how to obtain a different prediction. We posit that effective counterfactual explanations should satisfy two properties: feasibility of the counterfactual actions given user context and constraints, and diversity among the counterfactuals presented. To this end, we propose a framework for generating and evaluating a diverse set of counterfactual explanations based on determinantal point processes. To evaluate the actionability of counterfactuals, we provide metrics that enable comparison of counterfactual-based methods to other local explanation methods. We further address necessary tradeoffs and point to causal implications in optimizing for counterfactuals. Our experiments on four real-world datasets show that our framework can generate a set of counterfactuals that are diverse and well approximate local decision boundaries, outperforming prior approaches to generating diverse counterfactuals. We provide an implementation of the framework at https://github.com/microsoft/DiCE.

cs.LG↗