arXiv subjects

Hemank Lamba

Publications and source records attributed to Hemank Lamba.

18 recordsLinked to original sources

arXiv2025

Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions

Do LLMs genuinely incorporate external definitions, or do they primarily rely on their parametric knowledge? To address these questions, we conduct controlled experiments across multiple explanation benchmark datasets (general and domain-specific) and label definition conditions, including expert-curated, LLM-generated, perturbed, and swapped definitions. Our results reveal that while explicit label definitions can enhance accuracy and explainability, their integration into an LLM's task-solving processes is neither guaranteed nor consistent, suggesting reliance on internalized representations in many cases. Models often default to their internal representations, particularly in general tasks, whereas domain-specific tasks benefit more from explicit definitions. These findings underscore the need for a deeper understanding of how LLMs process external knowledge alongside their pre-existing capabilities.

cs.CL↗

arXiv2025

Operationalizing AI for Good: Spotlight on Deployment and Integration of AI Models in Humanitarian Work

Publications in the AI for Good space have tended to focus on the research and model development that can support high-impact applications. However, very few AI for Good papers discuss the process of deploying and collaborating with the partner organization, and the resulting real-world impact. In this work, we share details about the close collaboration with a humanitarian-to-humanitarian (H2H) organization and how to not only deploy the AI model in a resource-constrained environment, but also how to maintain it for continuous performance updates, and share key takeaways for practitioners.

cs.CL↗

arXiv2025

NLP for Social Good: A Survey and Outlook of Challenges, Opportunities, and Responsible Deployment

Natural language processing (NLP) now shapes many aspects of our world, yet its potential for positive social impact is underexplored. This paper surveys work in ``NLP for Social Good" (NLP4SG) across nine domains relevant to global development and risk agendas, summarizing principal tasks and challenges. We analyze ACL Anthology trends, finding that inclusion and AI harms attract the most research, while domains such as poverty, peacebuilding, and environmental protection remain underexplored. Guided by our review, we outline opportunities for responsible and equitable NLP and conclude with a call for cross-disciplinary partnerships and human-centered approaches to ensure that future NLP technologies advance the public good.

cs.CL↗

arXiv2024

CEHA: A Dataset of Conflict Events in the Horn of Africa

Natural Language Processing (NLP) of news articles can play an important role in understanding the dynamics and causes of violent conflict. Despite the availability of datasets categorizing various conflict events, the existing labels often do not cover all of the fine-grained violent conflict event types relevant to areas like the Horn of Africa. In this paper, we introduce a new benchmark dataset Conflict Events in the Horn of Africa region (CEHA) and propose a new task for identifying violent conflict events using online resources with this dataset. The dataset consists of 500 English event descriptions regarding conflict events in the Horn of Africa region with fine-grained event-type definitions that emphasize the cause of the conflict. This dataset categorizes the key types of conflict risk according to specific areas required by stakeholders in the Humanitarian-Peace-Development Nexus. Additionally, we conduct extensive experiments on two tasks supported by this dataset: Event-relevance Classification and Event-type Classification. Our baseline models demonstrate the challenging nature of these tasks and the usefulness of our dataset for model evaluations in low-resource settings with limited number of training data.

cs.CL↗

arXiv2024

Uchaguzi-2022: A Dataset of Citizen Reports on the 2022 Kenyan Election

Online reporting platforms have enabled citizens around the world to collectively share their opinions and report in real time on events impacting their local communities. Systematically organizing (e.g., categorizing by attributes) and geotagging large amounts of crowdsourced information is crucial to ensuring that accurate and meaningful insights can be drawn from this data and used by policy makers to bring about positive change. These tasks, however, typically require extensive manual annotation efforts. In this paper we present Uchaguzi-2022, a dataset of 14k categorized and geotagged citizen reports related to the 2022 Kenyan General Election containing mentions of election-related issues such as official misconduct, vote count irregularities, and acts of violence. We use this dataset to investigate whether language models can assist in scalably categorizing and geotagging reports, thus highlighting its potential application in the AI for Social Good space.

cs.CL↗

arXiv2024

HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid

Humanitarian organizations can enhance their effectiveness by analyzing data to discover trends, gather aggregated insights, manage their security risks, support decision-making, and inform advocacy and funding proposals. However, data about violent incidents with direct impact and relevance for humanitarian aid operations is not readily available. An automatic data collection and NLP-backed classification framework aligned with humanitarian perspectives can help bridge this gap. In this paper, we present HumVI - a dataset comprising news articles in three languages (English, French, Arabic) containing instances of different types of violent incidents categorized by the humanitarian sector they impact, e.g., aid security, education, food security, health, and protection. Reliable labels were obtained for the dataset by partnering with a data-backed humanitarian organization, Insecurity Insight. We provide multiple benchmarks for the dataset, employing various deep learning architectures and techniques, including data augmentation and mask loss, to address different task-related challenges, e.g., domain expansion. The dataset is publicly available at https://github.com/dataminr-ai/humvi-dataset.

cs.CL↗

arXiv2024

Explain then Rank: Scale Calibration of Neural Rankers Using Natural Language Explanations from LLMs

In search settings, calibrating the scores during the ranking process to quantities such as click-through rates or relevance levels enhances a system's usefulness and trustworthiness for downstream users. While previous research has improved this notion of calibration for low complexity learning-to-rank models, the larger data demands and parameter count specific to modern neural text rankers produce unique obstacles that hamper the efficacy of methods intended for the learning-to-rank setting. This paper proposes exploiting large language models (LLMs) to provide relevance and uncertainty signals for these neural text rankers to produce scale-calibrated scores through Monte Carlo sampling of natural language explanations (NLEs). Our approach transforms the neural ranking task from ranking textual query-document pairs to ranking corresponding synthesized NLEs. Comprehensive experiments on two popular document ranking datasets show that the NLE-based calibration approach consistently outperforms past calibration methods and LLM-based methods for ranking, calibration, and query performance prediction tasks.

cs.IR↗

arXiv2024

Dissecting users' needs for search result explanations

There is a growing demand for transparency in search engines to understand how search results are curated and to enhance users' trust. Prior research has introduced search result explanations with a focus on how to explain, assuming explanations are beneficial. Our study takes a step back to examine if search explanations are needed and when they are likely to provide benefits. Additionally, we summarize key characteristics of helpful explanations and share users' perspectives on explanation features provided by Google and Bing. Interviews with non-technical individuals reveal that users do not always seek or understand search explanations and mostly desire them for complex and critical tasks. They find Google's search explanations too obvious but appreciate the ability to contest search results. Based on our findings, we offer design recommendations for search engines and explanations to help users better evaluate search results and enhance their search experience.

cs.HC↗

arXiv2023

Counterfactual Editing for Search Result Explanation

Search Result Explanation (SeRE) aims to improve search sessions' effectiveness and efficiency by helping users interpret documents' relevance. Existing works mostly focus on factual explanation, i.e. to find/generate supporting evidence about documents' relevance to search queries. However, research in cognitive sciences has shown that human explanations are contrastive i.e. people explain an observed event using some counterfactual events; such explanations reduce cognitive load and provide actionable insights. Though already proven effective in machine learning and NLP communities, there lacks a strict formulation on how counterfactual explanations should be defined and structured, in the context of web search. In this paper, we first discuss the possible formulation of counterfactual explanations in the IR context. Next, we formulate a suite of desiderata for counterfactual explanation in SeRE task and corresponding automatic metrics. With this desiderata, we propose a method named \textbf{C}ounter\textbf{F}actual \textbf{E}diting for Search Research \textbf{E}xplanation (\textbf{CFE2}). CFE2 provides pairwise counterfactual explanations for document pairs within a search engine result page. Our experiments on five public search datasets demonstrate that CFE2 can significantly outperform baselines in both automatic metrics and human evaluations.

cs.IR↗

arXiv2022

Co-WIN: Really Winning? Analysing Inequity in India's Vaccination Response

The COVID-19 pandemic has so far accounted for reported 5.5M deaths worldwide, with 8.7% of these coming from India. The pandemic exacerbated the weakness of the Indian healthcare system. As of January 20, 2022, India is the second worst affected country with 38.2M reported cases and 487K deaths. According to epidemiologists, vaccines are an essential tool to prevent the spread of the pandemic. India's vaccination drive began on January 16, 2021 with governmental policies being introduced to prioritize different populations of the society. Through the course of the vaccination drive, multiple new policies were also introduced to ensure that vaccines are readily available and vaccination coverage is increased. However, at the same time, some of the government policies introduced led to unintended inequities in the populations being targeted. In this report, we enumerate and analyze the inequities that existed in India's vaccination policy drive, and also compute the effect of the new policies that were introduced. We analyze these potential inequities not only qualitatively but also quantitatively by leveraging the data that was made available through the government portals. Specifically, (a) we discover inequities that might exist in the policies, (b) we quantify the effect of new policies introduced to increase vaccination coverage, and (c) we also point the data discrepancies that exist across different data sources.

cs.CY↗

arXiv2022

Glowing Experience or Bad Trip? A Quantitative Analysis of User Reported Drug Experiences on Erowid.org

Erowid.org is a website dedicated to documenting information about psychoactive substances, with over 36,000 user-submitted drug Experience Reports. We study the potential of these reports to provide information about characteristic experiences with drugs. First, we assess different kinds of drug experiences, such as 'addiction' or 'bad trips'. We quantitatively analyze how such experiences are related to substances and user variables. Furthermore, we classify positive and negative experiences as well as reported addiction using information about the consumer, substance, context and location of the drug experience. While variables based only on objective characteristics yield poor predictive performance for subjective experiences, we find subjective user reports can help to identify new patterns and impact factors on drug experiences. In particular, we found a positive association between addiction experiences and dextromethorphan, a substance with largely unknown withdrawal effects. Our research can help to gain a deeper sociological understanding of drug consumption and to identify relationships which may have clinical relevance. Moreover, it can show how non-mainstream social media platforms can be utilized to study characteristics of human behavior and how this can be done in an ethical way in collaboration with the platform providers.

cs.SI↗

arXiv2021

Empirical observation of negligible fairness-accuracy trade-offs in machine learning for public policy

Growing use of machine learning in policy and social impact settings have raised concerns for fairness implications, especially for racial minorities. These concerns have generated considerable interest among machine learning and artificial intelligence researchers, who have developed new methods and established theoretical bounds for improving fairness, focusing on the source data, regularization and model training, or post-hoc adjustments to model scores. However, little work has studied the practical trade-offs between fairness and accuracy in real-world settings to understand how these bounds and methods translate into policy choices and impact on society. Our empirical study fills this gap by investigating the impact of mitigating disparities on accuracy, focusing on the common context of using machine learning to inform benefit allocation in resource-constrained programs across education, mental health, criminal justice, and housing safety. Here we describe applied work in which we find fairness-accuracy trade-offs to be negligible in practice. In each setting studied, explicitly focusing on achieving equity and using our proposed post-hoc disparity mitigation methods, fairness was substantially improved without sacrificing accuracy. This observation was robust across policy contexts studied, scale of resources available for intervention, time, and relative size of the protected groups. These empirical results challenge a commonly held assumption that reducing disparities either requires accepting an appreciable drop in accuracy or the development of novel, complex methods, making reducing disparities in these applications more practical.

cs.LG↗

arXiv2021

An Empirical Comparison of Bias Reduction Methods on Real-World Problems in High-Stakes Policy Settings

Applications of machine learning (ML) to high-stakes policy settings -- such as education, criminal justice, healthcare, and social service delivery -- have grown rapidly in recent years, sparking important conversations about how to ensure fair outcomes from these systems. The machine learning research community has responded to this challenge with a wide array of proposed fairness-enhancing strategies for ML models, but despite the large number of methods that have been developed, little empirical work exists evaluating these methods in real-world settings. Here, we seek to fill this research gap by investigating the performance of several methods that operate at different points in the ML pipeline across four real-world public policy and social good problems. Across these problems, we find a wide degree of variability and inconsistency in the ability of many of these methods to improve model fairness, but post-processing by choosing group-specific score thresholds consistently removes disparities, with important implications for both the ML research community and practitioners deploying machine learning to inform consequential policy decisions.

cs.LG↗

arXiv2020

Explainable Machine Learning for Public Policy: Use Cases, Gaps, and Research Directions

Explainability is highly-desired in Machine Learning (ML) systems supporting high-stakes policy decisions in areas such as health, criminal justice, education, and employment. While the field of explainable ML has expanded in recent years, much of this work has not taken real-world needs into account. A majority of proposed methods are designed with \textit{generic} explainability goals without well-defined use-cases or intended end-users and evaluated on simplified tasks, benchmark problems/datasets, or with proxy users (e.g., AMT). We argue that these simplified evaluation settings do not capture the nuances and complexities of real-world applications. As a result, the applicability and effectiveness of this large body of theoretical and methodological work in real-world applications are unclear. In this work, we take steps toward addressing this gap for the domain of public policy. First, we identify the primary use-cases of explainable ML within public policy problems. For each use case, we define the end-users of explanations and the specific goals the explanations have to fulfill. Finally, we map existing work in explainable ML to these use-cases, identify gaps in established capabilities, and propose research directions to fill those gaps to have a practical societal impact through ML. The contribution is 1) a methodology for explainable ML researchers to identify use cases and develop methods targeted at them and 2) using that methodology for the domain of public policy and giving an example for the researchers on developing explainable ML methods that result in real-world impact.

cs.LG↗

arXiv2019

Driving The Last Mile: Characterizing and Understanding Distracted Driving Posts on Social Networks

In 2015, 391,000 people were injured due to distracted driving in the US. One of the major reasons behind distracted driving is the use of cell-phones, accounting for 14% of fatal crashes. Social media applications have enabled users to stay connected, however, the use of such applications while driving could have serious repercussions -- often leading the user to be distracted from the road and ending up in an accident. In the context of impression management, it has been discovered that individuals often take a risk (such as teens smoking cigarettes, indulging in narcotics, and participating in unsafe sex) to improve their social standing. Therefore, viewing the phenomena of posting distracted driving posts under the lens of self-presentation, it can be hypothesized that users often indulge in risk-taking behavior on social media to improve their impression among their peers. In this paper, we first try to understand the severity of such social-media-based distractions by analyzing the content posted on a popular social media site where the user is driving and is also simultaneously creating content. To this end, we build a deep learning classifier to identify publicly posted content on social media that involves the user driving. Furthermore, a framework proposed to understand factors behind voluntary risk-taking activity observes that younger individuals are more willing to perform such activities, and men (as opposed to women) are more inclined to take risks. Grounding our observations in this framework, we test these hypotheses on 173 cities across the world. We conduct spatial and temporal analysis on a city-level and understand how distracted driving content posting behavior changes due to varied demographics. We discover that the factors put forth by the framework are significant in estimating the extent of such behavior.

cs.SI↗

arXiv2017

The Many Faces of Link Fraud

Most past work on social network link fraud detection tries to separate genuine users from fraudsters, implicitly assuming that there is only one type of fraudulent behavior. But is this assumption true? And, in either case, what are the characteristics of such fraudulent behaviors? In this work, we set up honeypots ("dummy" social network accounts), and buy fake followers (after careful IRB approval). We report the signs of such behaviors including oddities in local network connectivity, account attributes, and similarities and differences across fraud providers. Most valuably, we discover and characterize several types of fraud behaviors. We discuss how to leverage our insights in practice by engineering strongly performing entropy-based features and demonstrating high classification accuracy. Our contributions are (a) instrumentation: we detail our experimental setup and carefully engineered data collection process to scrape Twitter data while respecting API rate-limits, (b) observations on fraud multimodality: we analyze our honeypot fraudster ecosystem and give surprising insights into the multifaceted behaviors of these fraudster types, and (c) features: we propose novel features that give strong (>0.95 precision/recall) discriminative power on ground-truth Twitter data.

cs.SI↗

arXiv2017

Item Recommendation with Evolving User Preferences and Experience

Current recommender systems exploit user and item similarities by collaborative filtering. Some advanced methods also consider the temporal evolution of item ratings as a global background process. However, all prior methods disregard the individual evolution of a user's experience level and how this is expressed in the user's writing in a review community. In this paper, we model the joint evolution of user experience, interest in specific item facets, writing style, and rating behavior. This way we can generate individual recommendations that take into account the user's maturity level (e.g., recommending art movies rather than blockbusters for a cinematography expert). As only item ratings and review texts are observables, we capture the user's experience and interests in a latent model learned from her reviews, vocabulary and writing style. We develop a generative HMM-LDA model to trace user evolution, where the Hidden Markov Model (HMM) traces her latent experience progressing over time -- with solely user reviews and ratings as observables over time. The facets of a user's interest are drawn from a Latent Dirichlet Allocation (LDA) model derived from her reviews, as a function of her (again latent) experience level. In experiments with five real-world datasets, we show that our model improves the rating prediction over state-of-the-art baselines, by a substantial margin. We also show, in a use-case study, that our model performs well in the assessment of user experience levels.

cs.AI↗

arXiv2016

Me, Myself and My Killfie: Characterizing and Preventing Selfie Deaths

Over the past couple of years, clicking and posting selfies has become a popular trend. However, since March 2014, 127 people have died and many have been injured while trying to click a selfie. Researchers have studied selfies for understanding the psychology of the authors, and understanding its effect on social media platforms. In this work, we perform a comprehensive analysis of the selfie-related casualties and infer various reasons behind these deaths. We use inferences from incidents and from our understanding of the features, we create a system to make people more aware of the dangerous situations in which these selfies are taken. We use a combination of text-based, image-based and location-based features to classify a particular selfie as dangerous or not. Our method ran on 3,155 annotated selfies collected on Twitter gave 73% accuracy. Individually the image-based features were the most informative for the prediction task. The combination of image-based and location-based features resulted in the best accuracy. We have made our code and dataset available at http://labs.precog.iiitd.edu.in/killfie.

cs.SI↗