arXiv subjects

Pushpdeep Singh

Publications and source records attributed to Pushpdeep Singh.

5 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

Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization

The growing complexity of content moderation policies presents a critical challenge for their consistent operationalization. While foundation models possess the basic capabilities needed to confront this challenge, whether they can reliably moderate online content remains an unanswered question. In this paper, we systematically compare two competing paradigms for Vision-Language Model (VLM) guidance: an instruction-driven approach where models reason from policy precepts, and an example-driven approach where they generalize from prior precedents. We ground this investigation in ModerationBench, a new benchmark of 4,000 manually annotated, in-the-wild posts from the Bluesky platform. Our experiments reveal that foundation models can substantially outperform Bluesky's deployed moderation system, nearly tripling its $F_1$ score (0.60 vs. 0.22) on Random Posts in the benchmark, with both instruction- and example-driven paradigms achieving comparable peak effectiveness. Our findings thus chart a path toward reliable and adaptable policy operationalization at scale.

cs.CL↗

arXiv2024

Translating Across Cultures: LLMs for Intralingual Cultural Adaptation

LLMs are increasingly being deployed for multilingual applications and have demonstrated impressive translation capabilities between several low and high-resource languages. An aspect of translation that often gets overlooked is that of cultural adaptation, or modifying source culture references to suit the target culture. While specialized translation models still outperform LLMs on the machine translation task when viewed from the lens of correctness, they are not sensitive to cultural differences often requiring manual correction. LLMs on the other hand have a rich reservoir of cultural knowledge embedded within its parameters that can be potentially exploited for such applications. In this paper, we define the task of cultural adaptation and create an evaluation framework to evaluate the performance of modern LLMs for cultural adaptation and analyze their cross-cultural knowledge while connecting related concepts across different cultures. We also analyze possible issues with automatic adaptation. We hope that this task will offer more insight into the cultural understanding of LLMs and their creativity in cross-cultural scenarios.

cs.CL↗

arXiv2023

Don't Overlook the Grammatical Gender: Bias Evaluation for Hindi-English Machine Translation

Neural Machine Translation (NMT) models, though state-of-the-art for translation, often reflect social biases, particularly gender bias. Existing evaluation benchmarks primarily focus on English as the source language of translation. For source languages other than English, studies often employ gender-neutral sentences for bias evaluation, whereas real-world sentences frequently contain gender information in different forms. Therefore, it makes more sense to evaluate for bias using such source sentences to determine if NMT models can discern gender from the grammatical gender cues rather than relying on biased associations. To illustrate this, we create two gender-specific sentence sets in Hindi to automatically evaluate gender bias in various Hindi-English (HI-EN) NMT systems. We emphasise the significance of tailoring bias evaluation test sets to account for grammatical gender markers in the source language.

cs.CL↗

arXiv2023

Gender Inflected or Bias Inflicted: On Using Grammatical Gender Cues for Bias Evaluation in Machine Translation

Neural Machine Translation (NMT) models are state-of-the-art for machine translation. However, these models are known to have various social biases, especially gender bias. Most of the work on evaluating gender bias in NMT has focused primarily on English as the source language. For source languages different from English, most of the studies use gender-neutral sentences to evaluate gender bias. However, practically, many sentences that we encounter do have gender information. Therefore, it makes more sense to evaluate for bias using such sentences. This allows us to determine if NMT models can identify the correct gender based on the grammatical gender cues in the source sentence rather than relying on biased correlations with, say, occupation terms. To demonstrate our point, in this work, we use Hindi as the source language and construct two sets of gender-specific sentences: OTSC-Hindi and WinoMT-Hindi that we use to evaluate different Hindi-English (HI-EN) NMT systems automatically for gender bias. Our work highlights the importance of considering the nature of language when designing such extrinsic bias evaluation datasets.

cs.CL↗