Gaurav Verma

Yiqiao Jin, Mohit Chandra, Gaurav Verma et al. · gatech

Large language models (LLMs) are transforming the ways the general public accesses and consumes information. Their influence is particularly pronounced in pivotal sectors like healthcare, where lay individuals are increasingly appropriating LLMs as conversational agents for everyday queries. While LLMs demonstrate impressive language understanding and generation proficiencies, concerns regarding their safety remain paramount in these high-stake domains. Moreover, the development of LLMs is disproportionately focused on English. It remains unclear how these LLMs perform in the context of non-English languages, a gap that is critical for ensuring equity in the real-world use of these systems.This paper provides a framework to investigate the effectiveness of LLMs as multi-lingual dialogue systems for healthcare queries. Our empirically-derived framework XlingEval focuses on three fundamental criteria for evaluating LLM responses to naturalistic human-authored health-related questions: correctness, consistency, and verifiability. Through extensive experiments on four major global languages, including English, Spanish, Chinese, and Hindi, spanning three expert-annotated large health Q&A datasets, and through an amalgamation of algorithmic and human-evaluation strategies, we found a pronounced disparity in LLM responses across these languages, indicating a need for enhanced cross-lingual capabilities. We further propose XlingHealth, a cross-lingual benchmark for examining the multilingual capabilities of LLMs in the healthcare context. Our findings underscore the pressing need to bolster the cross-lingual capacities of these models, and to provide an equitable information ecosystem accessible to all.

Manoj Niverthi, Gaurav Verma, Srijan Kumar

Moderators and automated methods enforce bans on malicious users who engage in disruptive behavior. However, malicious users can easily create a new account to evade such bans. Previous research has focused on other forms of online deception, like the simultaneous operation of multiple accounts by the same entities (sockpuppetry), impersonation of other individuals, and studying the effects of de-platforming individuals and communities. Here we conduct the first data-driven study of ban evasion, i.e., the act of circumventing bans on an online platform, leading to temporally disjoint operation of accounts by the same user. We curate a novel dataset of 8,551 ban evasion pairs (parent, child) identified on Wikipedia and contrast their behavior with benign users and non-evading malicious users. We find that evasion child accounts demonstrate similarities with respect to their banned parent accounts on several behavioral axes - from similarity in usernames and edited pages to similarity in content added to the platform and its psycholinguistic attributes. We reveal key behavioral attributes of accounts that are likely to evade bans. Based on the insights from the analyses, we train logistic regression classifiers to detect and predict ban evasion at three different points in the ban evasion lifecycle. Results demonstrate the effectiveness of our methods in predicting future evaders (AUC = 0.78), early detection of ban evasion (AUC = 0.85), and matching child accounts with parent accounts (MRR = 0.97). Our work can aid moderators by reducing their workload and identifying evasion pairs faster and more efficiently than current manual and heuristic-based approaches. Dataset is available https://github.com/srijankr/ban_evasion.

Gaurav Verma, Jiawei Zhou, Mohit Chandra et al. · gatech

Large artificial intelligence (AI) models have garnered significant attention for their remarkable, often "superhuman", performance on standardized benchmarks. However, when these models are deployed in high-stakes verticals such as healthcare, education, and law, they often reveal notable limitations. For instance, they exhibit brittleness to minor variations in input data, present contextually uninformed decisions in critical settings, and undermine user trust by confidently producing or reproducing inaccuracies. These challenges in applying large models necessitate cross-disciplinary innovations to align the models' capabilities with the needs of real-world applications. We introduce a framework that addresses this gap through a layer-wise abstraction of innovations aimed at meeting users' requirements with large models. Through multiple case studies, we illustrate how researchers and practitioners across various fields can operationalize this framework. Beyond modularizing the pipeline of transforming large models into useful "vertical systems", we also highlight the dynamism that exists within different layers of the framework. Finally, we discuss how our framework can guide researchers and practitioners to (i) optimally situate their innovations (e.g., when vertical-specific insights can empower broadly impactful vertical-agnostic innovations), (ii) uncover overlooked opportunities (e.g., spotting recurring problems across verticals to develop practically useful foundation models instead of chasing benchmarks), and (iii) facilitate cross-disciplinary communication of critical challenges (e.g., enabling a shared vocabulary for AI developers, domain experts, and human-computer interaction scholars). Project webpage: https://gaurav22verma.github.io/vertical-systems-with-large-ai-models/

Gaurav Verma, Niyati Chhaya, Vishwa Vinay

With rising concern around abusive and hateful behavior on social media platforms, we present an ensemble learning method to identify and analyze the linguistic properties of such content. Our stacked ensemble comprises of three machine learning models that capture different aspects of language and provide diverse and coherent insights about inappropriate language. The proposed approach provides comparable results to the existing state-of-the-art on the Twitter Abusive Behavior dataset (Founta et al. 2018) without using any user or network-related information; solely relying on textual properties. We believe that the presented insights and discussion of shortcomings of current approaches will highlight potential directions for future research.

Bakhtiyar Syed, Gaurav Verma, Balaji Vasan Srinivasan et al.

Given the recent progress in language modeling using Transformer-based neural models and an active interest in generating stylized text, we present an approach to leverage the generalization capabilities of a language model to rewrite an input text in a target author's style. Our proposed approach adapts a pre-trained language model to generate author-stylized text by fine-tuning on the author-specific corpus using a denoising autoencoder (DAE) loss in a cascaded encoder-decoder framework. Optimizing over DAE loss allows our model to learn the nuances of an author's style without relying on parallel data, which has been a severe limitation of the previous related works in this space. To evaluate the efficacy of our approach, we propose a linguistically-motivated framework to quantify stylistic alignment of the generated text to the target author at lexical, syntactic and surface levels. The evaluation framework is both interpretable as it leads to several insights about the model, and self-contained as it does not rely on external classifiers, e.g. sentiment or formality classifiers. Qualitative and quantitative assessment indicates that the proposed approach rewrites the input text with better alignment to the target style while preserving the original content better than state-of-the-art baselines.

Gaurav Verma, Balaji Vasan Srinivasan

With a growing interest in modeling inherent subjectivity in natural language, we present a linguistically-motivated process to understand and analyze the writing style of individuals from three perspectives: lexical, syntactic, and semantic. We discuss the stylistically expressive elements within each of these levels and use existing methods to quantify the linguistic intuitions related to some of these elements. We show that such a multi-level analysis is useful for developing a well-knit understanding of style - which is independent of the natural language task at hand, and also demonstrate its value in solving three downstream tasks: authors' style analysis, authorship attribution, and emotion prediction. We conduct experiments on a variety of datasets, comprising texts from social networking sites, user reviews, legal documents, literary books, and newswire. The results on the aforementioned tasks and datasets illustrate that such a multi-level understanding of style, which has been largely ignored in recent works, models style-related subjectivity in text and can be leveraged to improve performance on multiple downstream tasks both qualitatively and quantitatively.

Aadhavan M. Nambhi, Bhanu Prakash Reddy, Aarsh Prakash Agarwal et al.

Data analytics software applications have become an integral part of the decision-making process of analysts. Users of such a software face challenges due to insufficient product and domain knowledge, and find themselves in need of help. To alleviate this, we propose a task-aware command recommendation system, to guide the user on what commands could be executed next. We rely on topic modeling techniques to incorporate information about user's task into our models. We also present a help prediction model to detect if a user is in need of help, in which case the system proactively provides the aforementioned command recommendations. We leverage the log data of a web-based analytics software to quantify the superior performance of our neural models, in comparison to competitive baselines.

Gaurav Verma, Eeshan Gunesh Dhekane, Tanaya Guha

We introduce the problem of learning affective correspondence between audio (music) and visual data (images). For this task, a music clip and an image are considered similar (having true correspondence) if they have similar emotion content. In order to estimate this crossmodal, emotion-centric similarity, we propose a deep neural network architecture that learns to project the data from the two modalities to a common representation space, and performs a binary classification task of predicting the affective correspondence (true or false). To facilitate the current study, we construct a large scale database containing more than $3,500$ music clips and $85,000$ images with three emotion classes (positive, neutral, negative). The proposed approach achieves $61.67\%$ accuracy for the affective correspondence prediction task on this database, outperforming two relevant and competitive baselines. We also demonstrate that our network learns modality-specific representations of emotion (without explicitly being trained with emotion labels), which are useful for emotion recognition in individual modalities.