arXiv subjects

Anjali Singh

Publications and source records attributed to Anjali Singh.

At least 19 recordsLinked to original sources

arXiv2026

Hint-Writing with Deferred AI Assistance: Fostering Critical Engagement in Data Science Education

Generating hints for incorrect code is a cognitively demanding task that fosters learning and metacognitive development. This study investigates three designs for personalized, scalable, and reflective hint-writing activities within a data science course: (i) writing a hint independently, (ii) writing a hint with on-demand AI assistance, and (iii) deferred AI assistance, in which students first write a hint independently and then revise it with the help of an AI-generated one. We examine how AI support can scaffold the learning process without diminishing students' productive cognitive effort. Through a randomized controlled experiment with graduate-level students (N=97), we found that deferring AI assistance leads to the highest-quality hints. Further, this design helps students identify a wide range of mistakes they otherwise struggle to identify without any AI assistance. Students valued these activities as opportunities to practice debugging and critically engage with AI outputs--skills that are now critical for learners to acquire as programming becomes increasingly automated and the use of AI for learning grows. Our findings also highlight key considerations for designing student-AI collaborative learning experiences to sustain student engagement, maintain appropriate cognitive load, and mitigate negative effects of AI, such as introducing redundancies and extraneous information into student work.

cs.HC↗

arXiv2026

Impact of Multimodal and Conversational AI on Learning Outcomes and Experience

Multimodal Large Language Models (MLLMs) offer an opportunity to support multimedia learning through conversational systems grounded in educational content. However, while conversational AI is known to boost engagement, its impact on learning in visually-rich STEM domains remains under-explored. Moreover, there is limited understanding of how multimodality and conversationality jointly influence learning in generative AI systems. This work reports findings from a randomized controlled online study (N = 124) comparing three approaches to learning biology from textbook content: (1) a document-grounded conversational AI with interleaved text-and-image responses (MuDoC), (2) a document-grounded conversational AI with text-only responses (TexDoC), and (3) a textbook interface with semantic search and highlighting (DocSearch). Learners using MuDoC achieved the highest post-test scores and reported the most positive learning experience. Notably, while TexDoC was rated as significantly more engaging and easier to use than DocSearch, it led to the lowest post-test scores, revealing a disconnect between student perceptions and learning outcomes. Interpreted through the lens of the Cognitive Load Theory, these findings suggest that conversationality reduces extraneous load, while visual-verbal integration induced by multimodality increases germane load, leading to better learning outcomes. When conversationality is not complemented by multimodality, reduced cognitive effort may instead inflate perceived understanding without improving learning outcomes.

cs.HC↗

arXiv2026

MetaCues: Enabling Critical Engagement with Generative AI for Information Seeking and Sensemaking

Generative AI (GenAI) search tools are increasingly used for information seeking, yet their design tends to encourage cognitive offloading, which may lead to passive engagement, selective attention, and informational homogenization. Effective use requires metacognitive engagement to craft good prompts, verify AI outputs, and critically engage with information. We developed MetaCues, a novel GenAI-based interactive tool for information seeking that delivers metacognitive cues alongside AI responses and a note-taking interface to guide users' search and associated learning. Through an online study (N = 146), we compared MetaCues to a baseline tool without cues, across two broad search topics that required participants to explore diverse perspectives in order to make informed judgments. Preliminary findings regarding participants' search behavior show that MetaCues leads to increased confidence in attitudinal judgments about the search topic as well as broader inquiry, with the latter effect emerging primarily for the topic that was less controversial and with which participants had relatively less familiarity. Accordingly, we outline directions for future qualitative exploration of search interactions and inquiry patterns.

cs.HC↗

arXiv2026

Enhancing Critical Thinking in Generative AI Search with Metacognitive Prompts

The growing use of Generative AI (GenAI) conversational search tools has raised concerns about their effects on people's metacognitive engagement, critical thinking, and learning. As people increasingly rely on GenAI to perform tasks such as analyzing and applying information, they may become less actively engaged in thinking and learning. This study examines whether metacognitive prompts - designed to encourage people to pause, reflect, assess their understanding, and consider multiple perspectives - can support critical thinking during GenAI-based search. We conducted a user study (N=40) with university students to investigate the impact of metacognitive prompts on their thought processes and search behaviors while searching with a GenAI tool. We found that these prompts led to more active engagement, prompting students to explore a broader range of topics and engage in deeper inquiry through follow-up queries. Students reported that the prompts were especially helpful for considering overlooked perspectives, promoting evaluation of AI responses, and identifying key takeaways. Additionally, the effectiveness of these prompts was influenced by students' metacognitive flexibility. Our findings highlight the potential of metacognitive prompts to foster critical thinking and provide insights for designing and implementing metacognitive support in human-AI interactions.

cs.HC↗

arXiv2025

Protecting Human Cognition in the Age of AI

The rapid adoption of Generative AI (GenAI) is significantly reshaping human cognition, influencing how we engage with information, think, reason, and learn. This paper synthesizes existing literature on GenAI's effects on different aspects of human cognition. Drawing on Krathwohl's revised Bloom's Taxonomy and Dewey's conceptualization of reflective thought, we examine the mechanisms through which GenAI is affecting the development of different cognitive abilities. We focus on novices, such as students, who may lack both domain knowledge and an understanding of effective human-AI interaction. Accordingly, we provide implications for rethinking and designing educational experiences that foster critical thinking and deeper cognitive engagement.

cs.CY↗

arXiv2025

Towards a Multimodal Document-grounded Conversational AI System for Education

Multimedia learning using text and images has been shown to improve learning outcomes compared to text-only instruction. But conversational AI systems in education predominantly rely on text-based interactions while multimodal conversations for multimedia learning remain unexplored. Moreover, deploying conversational AI in learning contexts requires grounding in reliable sources and verifiability to create trust. We present MuDoC, a Multimodal Document-grounded Conversational AI system based on GPT-4o, that leverages both text and visuals from documents to generate responses interleaved with text and images. Its interface allows verification of AI generated content through seamless navigation to the source. We compare MuDoC to a text-only system to explore differences in learner engagement, trust in AI system, and their performance on problem-solving tasks. Our findings indicate that both visuals and verifiability of content enhance learner engagement and foster trust; however, no significant impact in performance was observed. We draw upon theories from cognitive and learning sciences to interpret the findings and derive implications, and outline future directions for the development of multimodal conversational AI systems in education.

cs.HC↗

arXiv2024

A regularisation technique to precisely infer limb darkening using transit measurements: can we estimate stellar surface magnetic fields?

The high-precision measurements of exoplanet transit light curves that are now available contain information about the planet properties, their orbital parameters, and stellar limb darkening (LD). Recent 3D magneto-hydrodynamical (MHD) simulations of stellar atmospheres have shown that LD depends on the photospheric magnetic field, and hence its precise determination can be used to estimate the field strength. Among existing LD laws, the uses of the simplest ones may lead to biased inferences, whereas the uses of complex laws typically lead to a large degeneracy among the LD parameters. We have developed a novel approach in which we use a complex LD model but with second derivative regularisation during the fitting process. Regularisation controls the complexity of the model appropriately and reduces the degeneracy among LD parameters, thus resulting in precise inferences. The tests on simulated data suggest that our inferences are not only precise but also accurate. This technique is used to re-analyse 43 transit light curves measured by the NASA Kepler and TESS missions. Comparisons of our LD inferences with the corresponding literature values show good agreement, while the precisions of our measurements are better by up to a factor of 2. We find that 1D non-magnetic model atmospheres fail to reproduce the observations while 3D MHD simulations are qualitatively consistent. The LD measurements, together with MHD simulations, confirm that Kepler-17, WASP-18, and KELT-24 have relatively high magnetic fields ($>200$ G). This study paves the way for estimating the stellar surface magnetic field using the LD measurements.

astro-ph.SR↗

arXiv2024

Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation

Generative AI and large language models hold great promise in enhancing programming education by automatically generating individualized feedback for students. We investigate the role of generative AI models in providing human tutor-style programming hints to help students resolve errors in their buggy programs. Recent works have benchmarked state-of-the-art models for various feedback generation scenarios; however, their overall quality is still inferior to human tutors and not yet ready for real-world deployment. In this paper, we seek to push the limits of generative AI models toward providing high-quality programming hints and develop a novel technique, GPT4Hints-GPT3.5Val. As a first step, our technique leverages GPT-4 as a ``tutor'' model to generate hints -- it boosts the generative quality by using symbolic information of failing test cases and fixes in prompts. As a next step, our technique leverages GPT-3.5, a weaker model, as a ``student'' model to further validate the hint quality -- it performs an automatic quality validation by simulating the potential utility of providing this feedback. We show the efficacy of our technique via extensive evaluation using three real-world datasets of Python programs covering a variety of concepts ranging from basic algorithms to regular expressions and data analysis using pandas library.

cs.AI↗

arXiv2024

"They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations

Large language models (LLMs) have emerged as an integral part of modern societies, powering user-facing applications such as personal assistants and enterprise applications like recruitment tools. Despite their utility, research indicates that LLMs perpetuate systemic biases. Yet, prior works on LLM harms predominantly focus on Western concepts like race and gender, often overlooking cultural concepts from other parts of the world. Additionally, these studies typically investigate "harm" as a singular dimension, ignoring the various and subtle forms in which harms manifest. To address this gap, we introduce the Covert Harms and Social Threats (CHAST), a set of seven metrics grounded in social science literature. We utilize evaluation models aligned with human assessments to examine the presence of covert harms in LLM-generated conversations, particularly in the context of recruitment. Our experiments reveal that seven out of the eight LLMs included in this study generated conversations riddled with CHAST, characterized by malign views expressed in seemingly neutral language unlikely to be detected by existing methods. Notably, these LLMs manifested more extreme views and opinions when dealing with non-Western concepts like caste, compared to Western ones such as race.

cs.CL↗

arXiv2024

Generative AI-Based Text Generation Methods Using Pre-Trained GPT-2 Model

This work delved into the realm of automatic text generation, exploring a variety of techniques ranging from traditional deterministic approaches to more modern stochastic methods. Through analysis of greedy search, beam search, top-k sampling, top-p sampling, contrastive searching, and locally typical searching, this work has provided valuable insights into the strengths, weaknesses, and potential applications of each method. Each text-generating method is evaluated using several standard metrics and a comparative study has been made on the performance of the approaches. Finally, some future directions of research in the field of automatic text generation are also identified.

cs.CL↗

arXiv2023

Building AI and Human Capital for Road Safety

AI is about learning algorithms and huge amounts of data and are drivers of economic growth -- what does this mean for the field of development studies? Can we re-orient to twin AI studies and development theory and practice to generate how development challenges are identified and researched? To do this a good grasp is needed of AI internal mechanisms and outcomes in addressing development issues -- this argument will be developed through a case study of the ADAS [Advanced Driver Assistance System] deployment in India. Over and above discussing the ADAS we bring an anthropological lens to understand the social context that surrounds the system. Focusing on bus drivers, we offer findings from a qualitative and ethnographic study of drivers in a collaborative effort to achieve road safety by deploying AI-driven technology and empowering stakeholders in the transport industry in India especially, bus drivers as critical actors in the city transport network.

cs.HC↗

arXiv2023

Bridging Learnersourcing and AI: Exploring the Dynamics of Student-AI Collaborative Feedback Generation

This paper explores the space of optimizing feedback mechanisms in complex domains, such as data science, by combining two prevailing approaches: Artificial Intelligence (AI) and learnersourcing. Towards addressing the challenges posed by each approach, this work compares traditional learnersourcing with an AI-supported approach. We report on the results of a randomized controlled experiment conducted with 72 Master's level students in a data visualization course, comparing two conditions: students writing hints independently versus revising hints generated by GPT-4. The study aimed to evaluate the quality of learnersourced hints, examine the impact of student performance on hint quality, gauge learner preference for writing hints with or without AI support, and explore the potential of the student-AI collaborative exercise in fostering critical thinking about LLMs. Based on our findings, we provide insights for designing learnersourcing activities leveraging AI support and optimizing students' learning as they interact with LLMs.

cs.HC↗

arXiv2021

Symmetry induced phonon renormalization in few layers of 2H-MoTe$_2$ transistors: Raman and first-principles studies

Understanding of electron-phonon coupling (EPC) in two dimensional (2D) materials manifesting as phonon renormalization is essential to their possible applications in nanoelectronics. Here we report in-situ Raman measurements of electrochemically top-gated 2, 3 and 7 layered 2H-MoTe$ _{2} $ channel based field-effect transistors (FETs). While the E$ ^{1}_{2g} $ and B$ _{2g} $ phonon modes exhibit frequency softening and linewidth broadening with hole doping concentration (\textit{p}) up to $\sim$ 2.3 $\times$10$ ^{13} $/cm$ ^{2} $, A$ _{1g}$ shows relatively small frequency hardening and linewidth sharpening. The dependence of frequency renormalization of the E$ ^{1}_{2g} $ mode on the number of layers in these 2D crystals confirms that hole doping occurs primarily in the top two layers, in agreement with recent predictions. We present first-principles density functional theory (DFT) analysis of bilayer MoTe$ _{2} $ that qualitatively captures our observations, and explain that a relatively stronger coupling of holes with E$ ^{1}_{2g} $ or B$ _{2g} $ modes as compared with the A$ _{1g} $ mode originates from the in-plane orbital character and symmetry of the states at valence band maximum (VBM). The contrast between the manifestation of EPC in monolayer MoS$ _{2} $ and those observed here in a few-layered MoTe$ _{2} $ demonstrates the role of the symmetry of phonons and electronic states in determining the EPC in these isostructural systems.

cond-mat.mes-hall↗

arXiv2021

Reimagining GNN Explanations with ideas from Tabular Data

Explainability techniques for Graph Neural Networks still have a long way to go compared to explanations available for both neural and decision decision tree-based models trained on tabular data. Using a task that straddles both graphs and tabular data, namely Entity Matching, we comment on key aspects of explainability that are missing in GNN model explanations.

cs.LG↗

arXiv2019

Adversarial Adaptation of Scene Graph Models for Understanding Civic Issues

Citizen engagement and technology usage are two emerging trends driven by smart city initiatives. Governments around the world are adopting technology for faster resolution of civic issues. Typically, citizens report issues, such as broken roads, garbage dumps, etc. through web portals and mobile apps, in order for the government authorities to take appropriate actions. Several mediums -- text, image, audio, video -- are used to report these issues. Through a user study with 13 citizens and 3 authorities, we found that image is the most preferred medium to report civic issues. However, analyzing civic issue related images is challenging for the authorities as it requires manual effort. Moreover, previous works have been limited to identifying a specific set of issues from images. In this work, given an image, we propose to generate a Civic Issue Graph consisting of a set of objects and the semantic relations between them, which are representative of the underlying civic issue. We also release two multi-modal (text and images) datasets, that can help in further analysis of civic issues from images. We present a novel approach for adversarial training of existing scene graph models that enables the use of scene graphs for new applications in the absence of any labelled training data. We conduct several experiments to analyze the efficacy of our approach, and using human evaluation, we establish the appropriateness of our model at representing different civic issues.

cs.AI↗

arXiv2018

Origin of the monolayer Raman signature in hexagonal boron nitride: a first-principles analysis

Monolayers of hexagonal boron nitride (h-BN) can in principle be identified by a Raman signature, consisting of an upshift in the frequency of the E2g vibrational mode with respect to the bulk value, but the origin of this shift (intrinsic or support-induced) is still debated. Herein we use density functional theory calculations to investigate whether there is an intrinsic Raman shift in the h-BN monolayer in comparison with the bulk. There is universal agreement among all tested functionals in predicting the magnitude of the frequency shift upon a variation in the in-plane cell parameter. It is clear that a small in-plane contraction can explain the Raman peak upshift from bulk to monolayer. However, we show that the larger in-plane parameter in the bulk (compared to the monolayer) results from non-local correlation effects, which cannot be accounted for by local functionals or those with empirical dispersion corrections. Using a non-local-correlation functional, we then investigate the effect of finite temperatures on the Raman signature. We demonstrate that bulk h-BN thermally expands in the direction perpendicular to the layers, while the intralayer distances slightly contract, in agreement with observed experimental behavior. Interestingly, the difference in in-plane cell parameter between bulk and monolayer decreases with temperature, and becomes very small at room temperature. We conclude that the different thermal expansion of bulk and monolayer partially "erases" the intrinsic Raman signature, accounting for its small magnitude in recent experiments on suspended samples.

cond-mat.mtrl-sci↗

arXiv2017

Pressure-induced Lifshitz transition in NbP: Raman, x-ray diffraction, electrical transport and density functional theory

We report high pressure Raman, synchrotron x-ray diffraction and electrical transport studies on Weyl semimetals NbP and TaP along with first-principles density functional theoretical (DFT) analysis. The frequencies of first-order Raman modes of NbP harden with increasing pressure and exhibit a slope change at P$_c$ $\sim$ 9 GPa, and its resistivity exhibits a minimum at P$_c$. The pressure-dependent volume of NbP exhibits a change in its bulk modulus from 207 GPa to 243 GPa at P$_c$. Using DFT calculations, we show that these anomalies are associated with pressure induced Lifshitz transition which involves appearance of electron and hole pockets in its electronic structure. In contrast, results of Raman and synchrotron x-ray diffraction experiments on TaP and DFT calculations show that TaP is quite robust under pressure and does not undergo any phase transition.

cond-mat.mtrl-sci↗

arXiv2017

Raman anomalies as signatures of pressure induced electronic topological and structural transitions in black phosphorus: Experiments and Theory

We report high pressure Raman experiments of Black phosphorus up to 24 GPa. The line widths of first order Raman modes A$^1_g$, B$_{2g}$ and A$^2_g$ of the orthorhombic phase show a minimum at 1.1 GPa. Our first-principles density functional analysis reveals that this is associated with the anomalies in electron-phonon coupling at the semiconductor to topological insulator transition through inversion of valence and conduction bands marking a change from trivial to nontrivial electronic topology. The frequencies of B$_{2g}$ and A$^2_g$ modes become anomalous in the rhombohedral phase at 7.4 GPa, and new modes appearing in the rhombohedral phase show anomalous softening with pressure. This is shown to originate from unusual structural evolution of black phosphorous with pressure, based on first-principles theoretical analysis.

cond-mat.str-el↗