arXiv subjects

Abhijnan Chakraborty

Publications and source records attributed to Abhijnan Chakraborty.

At least 19 recordsLinked to original sources

arXiv2026

Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms

Empirical research on content moderation is fundamentally constrained by the opaque deployment of moderation systems on major social media platforms. To this end, the recent emergence of decentralized platforms with transparent, public moderation logs presents an unprecedented opportunity for independent audits. In this work, we leverage this architectural transparency to conduct the first large-scale audit of the default moderation system on Bluesky, the Bluesky Moderation Service (BMS). Analyzing its 10.6M moderation labels from 2025, we investigate three foundational aspects: (i) its mechanism (the degree of automation versus human oversight), (ii) its efficacy (accuracy in detecting harms), and (iii) its purpose (the landscape of harms it identifies). Our findings reveal a human-AI collaborative system where labels for sexual and graphic content are applied automatically in seconds, while nuanced and high stakes labels require more human oversight, taking hours or days. Through a manual annotation study, we find the BMS operates with high precision (0.837), but struggles with low recall (0.222), with our annotators identifying 4.5$\times$ more harmful content than the moderation system in a random sample. Finally, unsupervised clustering of the most frequently applied labeled posts uncovers detected harms ranging from hostility in discourse toward protected groups to the spread of sexually explicit and other graphic content. Our work offers a look into the operational realities of a deployed moderation system, providing a concrete data-driven foundation for designing more effective and transparent moderation systems.

cs.CY↗

arXiv2026

RSTGCN: Railway-centric Spatio-Temporal Graph Convolutional Network for Train Delay Prediction

Accurate prediction of train delays is critical for efficient railway operations. While earlier approaches have largely focused on forecasting the exact delays of individual trains, studies on station-level delay prediction are somewhat sparse. To address this gap, we propose the Railway-centric Spatio-Temporal Graph Convolutional Network (RSTGCN), designed to forecast average arrival delays of all the incoming trains at a particular station for a particular time period. Our approach incorporates several architectural innovations and novel feature integrations, including train frequency-aware spatial attention, which significantly enhance predictive performance. To support this effort, we curate and release a comprehensive dataset for the entire Indian Railway Network (IRN), spanning 4,735 stations across 17 zones - the largest and most diverse railway network studied to date. We conduct extensive experiments using multiple state-of-the-art baselines, demonstrating consistent improvements across standard metrics. Specifically, RSTGCN outperforms the best baseline by 18% in MAE, 14% in MAPE, and 1-8% in RMSE on the IRN.

cs.LG↗

arXiv2026

ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues

Large Language Models increasingly suppress biased outputs when demographic identity is stated explicitly, yet may still exhibit implicit biases when identity is conveyed indirectly. Existing benchmarks use name based proxies to detect implicit biases, which carry weak associations with many social demographics and cannot extend to dimensions like age or socioeconomic status. We introduce ImplicitBBQ, a QA benchmark that evaluates implicit bias through characteristic based cues, demographically associated attributes that signal implicitly, across age, gender, region, religion, caste, and socioeconomic status. Evaluating 11 models, we find that implicit bias in ambiguous contexts is over six times higher than explicit bias in open weight models. Notably, this bias is distributed unevenly across demographics: caste emerges as the most severe while gender is the least affected. Safety prompting and chain-of-thought reasoning fail to substantially close this gap; even few-shot prompting, which reduces implicit bias by 79%, leaves caste bias at four times the level of any other dimension. These findings indicate that current alignment and prompting strategies address the surface of bias evaluation while leaving demographically associated stereotypic associations largely unresolved. We publicly release our code and dataset for model providers and researchers to benchmark potential mitigation techniques.

cs.CL↗

arXiv2026

Fair Distribution of Digital Payments: Balancing Transaction Flows for Regulatory Compliance

The concentration of digital payment transactions in just two UPI apps like PhonePe and Google Pay has raised concerns of duopoly in India s digital financial ecosystem. To address this, the National Payments Corporation of India (NPCI) has mandated that no single UPI app should exceed 30 percent of total transaction volume. Enforcing this cap, however, poses a significant computational challenge: how to redistribute user transactions across apps without causing widespread user inconvenience while maintaining capacity limits? In this paper, we formalize this problem as the Minimum Edge Activation Flow (MEAF) problem on a bipartite network of users and apps, where activating an edge corresponds to a new app installation. The objective is to ensure a feasible flow respecting app capacities while minimizing additional activations. We further prove that Minimum Edge Activation Flow is NP-Complete. To address the computational challenge, we propose scalable heuristics, named Decoupled Two-Stage Allocation Strategy (DTAS), that exploit flow structure and capacity reuse. Experiments on large semi-synthetic transaction network data show that DTAS finds solutions close to the optimal ILP within seconds, offering a fast and practical way to enforce transaction caps fairly and efficiently.

cs.NI↗

arXiv2026

LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reports

Citizen reporting platforms help the public and authorities stay informed about sexual harassment incidents. However, the high volume of data shared on these platforms makes reviewing each individual case challenging. Therefore, a summarization algorithm capable of processing and understanding various code-mixed languages is essential. In recent years, Large Language Models (LLMs) have shown exceptional performance in NLP tasks, including summarization. LLMs inherently produce abstractive summaries by paraphrasing the original text, while the generation of extractive summaries - selecting specific subsets from the original text - through LLMs remains largely unexplored. Moreover, LLMs have a limited context window size, restricting the amount of data that can be processed at once. We tackle these challenges by introducing LaMSUM, a novel multi-level framework combining summarization with different voting methods to generate extractive summaries for large collections of incident reports using LLMs. Extensive evaluation using four popular LLMs (Llama, Mistral, Claude and GPT-4o) demonstrates that LaMSUM outperforms state-of-the-art extractive summarization methods. Overall, this work represents one of the first attempts to achieve extractive summarization through LLMs, and is likely to support stakeholders by offering a comprehensive overview and enabling them to develop effective policies to minimize incidents of unwarranted harassment.

cs.CL↗

arXiv2026

Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion

Large Language Models (LLMs) are increasingly being deployed in multilingual, multicultural settings, yet their reliance on predominantly English-centric training data risks misalignment with the diverse cultural values of different societies. In this paper, we present a comprehensive, multilingual audit of the cultural alignment of contemporary LLMs including GPT-4o-Mini, Gemini-2.5-Flash, Llama 3.2, Mistral and Gemma 3 across India, East Asia and Southeast Asia. Our study specifically focuses on the sensitive domain of religion as the prism for broader alignment. To facilitate this, we conduct a multi-faceted analysis of every LLM's internal representations, using log-probs/logits, to compare the model's opinion distributions against ground-truth public attitudes. We find that while the popular models generally align with public opinion on broad social issues, they consistently fail to accurately represent religious viewpoints, especially those of minority groups, often amplifying negative stereotypes. Lightweight interventions, such as demographic priming and native language prompting, partially mitigate but do not eliminate these cultural gaps. We further show that downstream evaluations on bias benchmarks (such as CrowS-Pairs, IndiBias, ThaiCLI, KoBBQ) reveal persistent harms and under-representation in sensitive contexts. Our findings underscore the urgent need for systematic, regionally grounded audits to ensure equitable global deployment of LLMs.

cs.CL↗

arXiv2025

Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditions

Large Language Models (LLMs) have shown remarkable advancements but also raise concerns about cultural bias, often reflecting dominant narratives at the expense of under-represented subcultures. In this study, we evaluate the capacity of LLMs to recognize and accurately respond to the Little Traditions within Indian society, encompassing localized cultural practices and subcultures such as caste, kinship, marriage, and religion. Through a series of case studies, we assess whether LLMs can balance the interplay between dominant Great Traditions and localized Little Traditions. We explore various prompting strategies and further investigate whether using prompts in regional languages enhances the models cultural sensitivity and response quality. Our findings reveal that while LLMs demonstrate an ability to articulate cultural nuances, they often struggle to apply this understanding in practical, context-specific scenarios. To the best of our knowledge, this is the first study to analyze LLMs engagement with Indian subcultures, offering critical insights into the challenges of embedding cultural diversity in AI systems.

cs.CL↗

arXiv2025

SMITE: Enhancing Fairness in LLMs through Optimal In-Context Example Selection via Dynamic Validation

Large Language Models (LLMs) are widely used for downstream tasks such as tabular classification, where ensuring fairness in their outputs is critical for inclusivity, equal representation, and responsible AI deployment. This study introduces a novel approach to enhancing LLM performance and fairness through the concept of a dynamic validation set, which evolves alongside the test set, replacing the traditional static validation approach. We also propose an iterative algorithm, SMITE, to select optimal in-context examples, with each example set validated against its corresponding dynamic validation set. The in-context set with the lowest total error is used as the final demonstration set. Our experiments across four different LLMs show that our proposed techniques significantly improve both predictive accuracy and fairness compared to baseline methods. To our knowledge, this is the first study to apply dynamic validation in the context of in-context learning for LLMs.

cs.CL↗

arXiv2025

Rethinking Hate Speech Detection on Social Media: Can LLMs Replace Traditional Models?

Hate speech detection across contemporary social media presents unique challenges due to linguistic diversity and the informal nature of online discourse. These challenges are further amplified in settings involving code-mixing, transliteration, and culturally nuanced expressions. While fine-tuned transformer models, such as BERT, have become standard for this task, we argue that recent large language models (LLMs) not only surpass them but also redefine the landscape of hate speech detection more broadly. To support this claim, we introduce IndoHateMix, a diverse, high-quality dataset capturing Hindi-English code-mixing and transliteration in the Indian context, providing a realistic benchmark to evaluate model robustness in complex multilingual scenarios where existing NLP methods often struggle. Our extensive experiments show that cutting-edge LLMs (such as LLaMA-3.1) consistently outperform task-specific BERT-based models, even when fine-tuned on significantly less data. With their superior generalization and adaptability, LLMs offer a transformative approach to mitigating online hate in diverse environments. This raises the question of whether future works should prioritize developing specialized models or focus on curating richer and more varied datasets to further enhance the effectiveness of LLMs.

cs.CL↗

arXiv2025

Sometimes the Model doth Preach: Quantifying Religious Bias in Open LLMs through Demographic Analysis in Asian Nations

Large Language Models (LLMs) are capable of generating opinions and propagating bias unknowingly, originating from unrepresentative and non-diverse data collection. Prior research has analysed these opinions with respect to the West, particularly the United States. However, insights thus produced may not be generalized in non-Western populations. With the widespread usage of LLM systems by users across several different walks of life, the cultural sensitivity of each generated output is of crucial interest. Our work proposes a novel method that quantitatively analyzes the opinions generated by LLMs, improving on previous work with regards to extracting the social demographics of the models. Our method measures the distance from an LLM's response to survey respondents, through Hamming Distance, to infer the demographic characteristics reflected in the model's outputs. We evaluate modern, open LLMs such as Llama and Mistral on surveys conducted in various global south countries, with a focus on India and other Asian nations, specifically assessing the model's performance on surveys related to religious tolerance and identity. Our analysis reveals that most open LLMs match a single homogeneous profile, varying across different countries/territories, which in turn raises questions about the risks of LLMs promoting a hegemonic worldview, and undermining perspectives of different minorities. Our framework may also be useful for future research investigating the complex intersection between training data, model architecture, and the resulting biases reflected in LLM outputs, particularly concerning sensitive topics like religious tolerance and identity.

cs.CY↗

arXiv2025

MARRO: Multi-headed Attention for Rhetorical Role Labeling in Legal Documents

Identification of rhetorical roles like facts, arguments, and final judgments is central to understanding a legal case document and can lend power to other downstream tasks like legal case summarization and judgment prediction. However, there are several challenges to this task. Legal documents are often unstructured and contain a specialized vocabulary, making it hard for conventional transformer models to understand them. Additionally, these documents run into several pages, which makes it difficult for neural models to capture the entire context at once. Lastly, there is a dearth of annotated legal documents to train deep learning models. Previous state-of-the-art approaches for this task have focused on using neural models like BiLSTM-CRF or have explored different embedding techniques to achieve decent results. While such techniques have shown that better embedding can result in improved model performance, not many models have focused on utilizing attention for learning better embeddings in sentences of a document. Additionally, it has been recently shown that advanced techniques like multi-task learning can help the models learn better representations, thereby improving performance. In this paper, we combine these two aspects by proposing a novel family of multi-task learning-based models for rhetorical role labeling, named MARRO, that uses transformer-inspired multi-headed attention. Using label shift as an auxiliary task, we show that models from the MARRO family achieve state-of-the-art results on two labeled datasets for rhetorical role labeling, from the Indian and UK Supreme Courts.

cs.CL↗

arXiv2024

Investigating Nudges toward Related Sellers on E-commerce Marketplaces: A Case Study on Amazon

E-commerce marketplaces provide business opportunities to millions of sellers worldwide. Some of these sellers have special relationships with the marketplace by virtue of using their subsidiary services (e.g., fulfillment and/or shipping services provided by the marketplace) -- we refer to such sellers collectively as Related Sellers. When multiple sellers offer to sell the same product, the marketplace helps a customer in selecting an offer (by a seller) through (a) a default offer selection algorithm, (b) showing features about each of the offers and the corresponding sellers (price, seller performance metrics, seller's number of ratings etc.), and (c) finally evaluating the sellers along these features. In this paper, we perform an end-to-end investigation into how the above apparatus can nudge customers toward the Related Sellers on Amazon's four different marketplaces in India, USA, Germany and France. We find that given explicit choices, customers' preferred offers and algorithmically selected offers can be significantly different. We highlight that Amazon is adopting different performance metric evaluation policies for different sellers, potentially benefiting Related Sellers. For instance, such policies result in notable discrepancy between the actual performance metric and the presented performance metric of Related Sellers. We further observe that among the seller-centric features visible to customers, sellers' number of ratings influences their decisions the most, yet it may not reflect the true quality of service by the seller, rather reflecting the scale at which the seller operates, thereby implicitly steering customers toward larger Related Sellers. Moreover, when customers are shown the rectified metrics for the different sellers, their preference toward Related Sellers is almost halved.

cs.CY↗

arXiv2024

Artificial Intelligence (AI) in Legal Data Mining

Despite the availability of vast amounts of data, legal data is often unstructured, making it difficult even for law practitioners to ingest and comprehend the same. It is important to organise the legal information in a way that is useful for practitioners and downstream automation tasks. The word ontology was used by Greek philosophers to discuss concepts of existence, being, becoming and reality. Today, scientists use this term to describe the relation between concepts, data, and entities. A great example for a working ontology was developed by Dhani and Bhatt. This ontology deals with Indian court cases on intellectual property rights (IPR) The future of legal ontologies is likely to be handled by computer experts and legal experts alike.

cs.AI↗

arXiv2024

Can LLMs Help Predict Elections? (Counter)Evidence from the World's Largest Democracy

The study of how social media affects the formation of public opinion and its influence on political results has been a popular field of inquiry. However, current approaches frequently offer a limited comprehension of the complex political phenomena, yielding inconsistent outcomes. In this work, we introduce a new method: harnessing the capabilities of Large Language Models (LLMs) to examine social media data and forecast election outcomes. Our research diverges from traditional methodologies in two crucial respects. First, we utilize the sophisticated capabilities of foundational LLMs, which can comprehend the complex linguistic subtleties and contextual details present in social media data. Second, we focus on data from X (Twitter) in India to predict state assembly election outcomes. Our method entails sentiment analysis of election-related tweets through LLMs to forecast the actual election results, and we demonstrate the superiority of our LLM-based method against more traditional exit and opinion polls. Overall, our research offers valuable insights into the unique dynamics of Indian politics and the remarkable impact of social media in molding public attitudes within this context.

cs.SI↗

arXiv2024

Antitrust, Amazon, and Algorithmic Auditing

In digital markets, antitrust law and special regulations aim to ensure that markets remain competitive despite the dominating role that digital platforms play today in everyone's life. Unlike traditional markets, market participant behavior is easily observable in these markets. We present a series of empirical investigations into the extent to which Amazon engages in practices that are typically described as self-preferencing. We discuss how the computer science tools used in this paper can be used in a regulatory environment that is based on algorithmic auditing and requires regulating digital markets at scale.

cs.CY↗

arXiv2024

Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification

Employing Large Language Models (LLM) in various downstream applications such as classification is crucial, especially for smaller companies lacking the expertise and resources required for fine-tuning a model. Fairness in LLMs helps ensure inclusivity, equal representation based on factors such as race, gender and promotes responsible AI deployment. As the use of LLMs has become increasingly prevalent, it is essential to assess whether LLMs can generate fair outcomes when subjected to considerations of fairness. In this study, we introduce a framework outlining fairness regulations aligned with various fairness definitions, with each definition being modulated by varying degrees of abstraction. We explore the configuration for in-context learning and the procedure for selecting in-context demonstrations using RAG, while incorporating fairness rules into the process. Experiments conducted with different LLMs indicate that GPT-4 delivers superior results in terms of both accuracy and fairness compared to other models. This work is one of the early attempts to achieve fairness in prediction tasks by utilizing LLMs through in-context learning.

cs.CL↗

arXiv2024

Towards Fair Allocation in Social Commerce Platforms

Social commerce platforms are emerging businesses where producers sell products through re-sellers who advertise the products to other customers in their social network. Due to the increasing popularity of this business model, thousands of small producers and re-sellers are starting to depend on these platforms for their livelihood; thus, it is important to provide fair earning opportunities to them. The enormous product space in such platforms prohibits manual search, and motivates the need for recommendation algorithms to effectively allocate product exposure and, consequently, earning opportunities. In this work, we focus on the fairness of such allocations in social commerce platforms and formulate the problem of assigning products to re-sellers as a fair division problem with indivisible items under two-sided cardinality constraints, wherein each product must be given to at least a certain number of re-sellers and each re-seller must get a certain number of products. Our work systematically explores various well-studied benchmarks of fairness -- including Nash social welfare, envy-freeness up to one item (EF1), and equitability up to one item (EQ1) -- from both theoretical and experimental perspectives. We find that the existential and computational guarantees of these concepts known from the unconstrained setting do not extend to our constrained model. To address this limitation, we develop a mixed-integer linear program and other scalable heuristics that provide near-optimal approximation of Nash social welfare in simulated and real social commerce datasets. Overall, our work takes the first step towards achieving provable fairness alongside reasonable revenue guarantees on social commerce platforms.

cs.CY↗