Hello!

Selected Publications

1. Pooja S. B. Rao, Laxminarayen Nagarajan Venkatesan, Dinesh Babu Jayagopi, and Mauro Cherubini, “Robotic Answers: Participatory Identification of Risks in AI-Assisted Interview Training by Job Seekers” ACM Conference on Fairness, Accountability, and Transparency (FAccT) 2026.
2. Pooja S. B. Rao, Sanja Šćepanović, Dinesh Babu Jayagopi, Mauro Cherubini, and Daniele Quercia, “The AI Model Risk Catalog: What Developers and Researchers Miss About Real-World AI Harms.” AAAI/ACM Conference on AI, Ethics, and Society (AIES) 2025.
3. Pooja S. B. Rao, Laxminarayen Nagarajan Venkatesan, Mauro Cherubini, and Dinesh Babu Jayagopi, “Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models.” AAAI/ACM Conference on AI, Ethics, and Society (AIES) 2025.
4. Dhruv Awasthi, Pooja S. B. Rao, and Dinesh Babu Jayagopi, “ResumeGenAI: Supporting Job Seekers with LLM-Driven Resume Feedback.” ACM Conference on Conversational User Interfaces (CUI) 2025.
5. Pooja S. B. Rao, Sanja Šćepanović, Ke Zhou, Edyta Paulina Bogucka, Daniele Quercia, “RiskRAG: A Data-Driven Solution for Improved AI Model Risk Reporting.” ACM CHI Conference on Human Factors in Computing Systems (CHI ’25) 2025.
6. Pooja S. B. Rao, Laetitia Renier, Marc-Olivier Boldi, Marianne S. Mast, Dinesh B. Jayagopi and Mauro Cherubini, “On the Potential of Supporting Autonomy in Online Video Interview Training Platforms.” International Journal of Human-Computer Studies (IJHCS) 2024.
7. Kavous S. Niksirat, Lahari Goswami, Pooja S. B. Rao, James Tyler, Alessandro Silacci, Sadiq Aliyu, Annika Aebil, Chat Wacharamanotham, Mauro Cherubini, “Changes in Research Ethics, Openness, and Transparency in Empirical Studies between CHI 2017 and CHI 2022.” ACM CHI Conference on Human Factors in Computing Systems (CHI ’23) 2023. 🏆 Best Paper Award (Top 1%)
8. Pooja S. B. Rao, Dinesh B. Jayagopi and Mauro Cherubini, “Explainability in Automated Training and Feedback Systems.” ACM CHI Workshop Human-Centered Perspectives in Explainable AI (HCXAI) 2022.
9. Jinal Hitesh Thakkar, Pooja S. B. Rao, Kumar Shubham, Dinesh B. Jayagopi, “Understanding Interviewees’ Perceptions and Behaviour towards Verbally and Non-verbally Expressive Virtual Interviewing Agents.” Companion Publication of the 2022 International Conference on Multimodal Interaction (ICMI) 2022.
10. Vibhav Agarwal, Pooja S. B. Rao, and Dinesh B. Jayagopi, “Towards Code-Mixed Hinglish Dialogue Generation.” 3rd Workshop on Natural Language Processing for Conversational AI (NLP4ConvAI) held with EMNLP 2021
11. Pooja S. B. Rao, Manish Agnihotri and Dinesh B. Jayagopi, “Improving Asynchronous Interview Interaction with Follow-up Question Generation.” International Journal of Interactive Multimedia & Artificial Intelligence (IJIMAI) 2021.
12. Pooja S. B. Rao, Manish Agnihotri and Dinesh B. Jayagopi, “Incorporating Automatic Follow-up Question Generation for Asynchronous Interviews.” Workshop on Intelligent Information Processing and Natural Language Generation, ECAI, 2020.
13. Pooja S. B. Rao, Sowmya Rasipuram, Rahul Das, and Dinesh B. Jayagopi, “Automatic Assessment of Communication Skill in Non-conventional Interview Settings: A Comparative Study.” 19th ACM International Conference on Multimodal Interaction (ICMI) 2017
14. Sowmya Rasipuram, Pooja S. B. Rao, and Dinesh B. Jayagopi, “Automatic Prediction of Fluency in Interface-Based Interviews.” In India Conference (INDICON) 2016 IEEE
15. Sowmya Rasipuram, Pooja S. B. Rao, and Dinesh B. Jayagopi, “Asynchronous Video Interviews vs. Face-to-Face Interviews for Communication Skill Measurement: A Systematic Study.” 18th ACM International Conference on Multimodal Interaction (ICMI) 2016. 🏆 Nominated for Best Student Paper.

Workshops Organized

Multimodal Machine Learning for Human Behaviour Understanding

AMLD 2024, EPFL, Lausanne, Switzerland • April 2024 • Materials & Repo

This workshop introduced participants to the foundations and applications of multimodal machine learning for human-centric AI applications. The goal was to provide a brief overview of how to process different modalities such as video, audio, and text, and to highlight how communication extends beyond words through facial expressions, tone, and non-verbal cues. We included hands-on code for extracting features from these modalities and demonstrated how multimodal fusion could support data-driven evaluation of interview communication skills by combining facial, acoustic, and textual signals.

---

Virtual Interviewer: Build your own interviewing agent

AMLD 2021, EPFL, Lausanne, Switzerland • April 2021 • Materials & Repo

This workshop aimed to build a virtual interviewing agent capable of asking dynamic follow-up questions. It was conducted in two parts: first, we showed how to build a follow-up question generation model using a pre-trained GPT-2 language model; second, we demonstrated how to deploy the model as a virtual interviewing agent using AWS Sumerian. The session combined model development with practical system deployment and gave participants a hands-on understanding of how conversational agents can support interview scenarios.

---

Procedure Detection Hands-on Session

R V College of Engineering, Bengaluru, India • 2020 • Materials & Repo

This hands-on session introduced participants to procedure detection and helped them understand how machine learning and computer vision techniques can be used to recognize and model activity sequences and procedural steps. It provided a practical overview of the underlying methods and demonstrated how these approaches can be applied to real-world activity understanding tasks.

PhD Thesis

Rising unemployment, exacerbated by global economic instability and evolving labor markets, has intensified the need for scalable and effective job preparation tools. Simultaneously, the rapid proliferation of Artificial Intelligence (AI), driven by declining deployment costs and increasing complexity, has fundamentally transformed recruitment practices worldwide. Amid these trends, job seekers face a paradox: while AI offers new avenues for support, it also introduces concerns about unfulfilled user needs, as well as opaque and potentially biased mechanisms of evaluation.

This thesis explores how AI is reshaping the landscape of job interview training while critically examining the risks these technologies pose. Through five interlinked studies, the research traces a progression from designing AI-enabled training systems to examining the broader risks accompanying their adoption in high-stakes settings such as hiring.

The first study introduces InterviewApp, an asynchronous video interview (AVI) training system designed using Self-Determination Theory, a psychological framework that emphasizes fulfillment of autonomy, competence, and relatedness as essential for self-determined motivation and learning. With InterviewApp, I examine how structured training and feedback can enhance job seekers’ interview motivation and performance. The intervention with job seekers demonstrates the mediating role of autonomy in influencing performance. Features such as mock interview recordings, playback, and expert feedback positively influence performance. Additionally, the study reveals a strong need for feedback that is personalized, actionable, and available repeatedly, which is challenging to meet through conventional human-led training alone.

The second study employs a participatory co-design methodology to envision how AI might fill this gap. This study collaboratively surfaces needs, constraints, and ethical concerns related to AI-assisted interview training systems by engaging two key stakeholder groups: job seekers and AI practitioners. Findings reveal the requirements job seekers value, their concerns, and practitioner insights into feasibility, pitfalls, and responsible development. It uncovers key tensions between job seekers' perceptions and AI practitioners' expertise around human–AI collaboration and accountability. The results highlight the four socio-psychological risks perceived by job seekers. These insights offer valuable design considerations for AI interview training systems, demonstrating the significance of stakeholder engagement in AI design for effective user-centered solutions.

The third study builds directly on the concerns raised during co-design, particularly around fairness. I examine how AI, particularly Large Language Models (LLMs), evaluate job interview responses across cultural contexts. Using a controlled dataset of video interview transcripts from UK and Indian job seekers, this analysis examines how LLMs rated attributes such as hirability, self-promotion, storytelling, and positive impression. The findings reveal systematic disparities: Indian transcripts consistently receive lower scores, even when anonymized. Linguistic features, such as syntactic complexity and lexical diversity, rather than identity cues like name or gender, are linked to these disparities. This study highlights the latent cultural biases embedded within LLMs and underscores the need for culturally sensitive evaluation systems in employment settings.

To address the broader implications of such biases, the final two studies interrogate the wider ecosystem of AI model risk communication and reporting. The fourth study introduces the AI Model Risk Catalog, compiled from nearly 460,000 human-written model documentation. Comparing developer-reported risks with real-world harms from the AI Incident Database and academic risk taxonomies, we identified major reporting gaps, specifically around fraud, manipulation, and social engineering, issues highly relevant to employment-related applications.

The fifth study introduces RiskRAG, a Retrieval-Augmented Generation tool designed to address these documentation shortcomings. Co-designed with AI developers, RiskRAG generates contextual, actionable risk reports tailored to specific models and their applications. User evaluations with practitioners show that RiskRAG improves risk awareness and model selection decisions, fostering more deliberative practices, particularly important in sensitive domains like hiring.

Together, these five studies offer a comprehensive examination of AI's role in job interview training, from system design and participatory development to fairness auditing and systematic risk identification and reporting. This thesis has valuable implications for developing effective tools for job seekers, but also contributes to the broader discourse on the responsible development of AI systems. It emphasizes the need to embed equity, transparency, and accountability across the AI lifecycle, particularly in domains that shape access to economic opportunity.

Full thesis can be found here

Professional Activities

• March 2025: Received the SIGCHI Gary Marsden Travel Award to attend CHI 2025 in Yokohama, Japan, supporting my participation in the global HCI research community.

• Jan 2024: Served as a student volunteer for CODS-COMAD in Bangalore, India, contributing to the smooth organization and delivery of the conference.

• July 2023: Delivered an invited talk on our CHI 2023 paper, “Changes in Research Ethics, Openness, and Transparency in Empirical Studies between CHI 2017 and CHI 2022,” at Nokia Bell Labs in Cambridge. The talk is available here.

• November 2022: Volunteered for ICMI 2022 in Bangalore, India, supporting the conference and enabling a successful research event.

• May 2022: Our opinion paper, “Explainability in Automated Training and Feedback Systems,” was accepted at the ACM CHI Workshop on Human-Centered Perspectives in Explainable AI (HCXAI 2022). The talk is available here.

• March 2022: Volunteered for AMLD 2022 in Lausanne, Switzerland, helping support a leading applied machine learning event.

• Reviewing: Actively contributing to the scientific community as a reviewer for CHI, AIES, CSCW, MobileHCI, and INTERACT, supporting the peer-review process in HCI and AI research.

Master Thesis

Work towards adding automated elements to asynchronous interview systems by solving the problems of interview follow-up question generation and automatic assessment of candidates using various Machine Learning techniques like text generation, text classification and transfer learning techniques for NLP.

• Automatic Follow-up Question Generation – enable a virtual interviewer to generate a follow-up question given a predetermined question and a candidate response using LSTM-based and Transformer models. (View demo)
• Automatic Assessment of Communication Skill – Supervised predictive models to assess the written communication skill scores of interview candidates in various non-conventional interview settings. (View thesis and defense slides)