@article{tocchetti_i_2025,

title = {Aİ. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities},

author = {A. Tocchetti and L. Corti and A. Balayn and M. Yurrita and P. Lippmann and M. Brambilla and J. Yang},

url = {https://dl.acm.org/doi/10.1145/3665926},

doi = {10.1145/3665926},

issn = {0360-0300},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-01},

journal = {ACM Comput. Surv.},

volume = {57},

number = {6},

pages = {141:1–141:38},

abstract = {Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Besides, robustness is interpreted differently across domains and contexts of AI. In this work, we systematically survey recent progress to provide a reconciled terminology of concepts around AI robustness. We introduce three taxonomies to organize and describe the literature both from a fundamental and applied point of view: (1) methods and approaches that address robustness in different phases of the machine learning pipeline; (2) methods improving robustness in specific model architectures, tasks, and systems; and in addition, (3) methodologies and insights around evaluating the robustness of AI systems, particularly the tradeoffs with other trustworthiness properties. Finally, we identify and discuss research gaps and opportunities and give an outlook on the field. We highlight the central role of humans in evaluating and enhancing AI robustness, considering the necessary knowledge they can provide, and discuss the need for better understanding practices and developing supportive tools in the future.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{arzberger_nothing_2024,

title = {Nothing Comes Without Its World – Practical Challenges of Aligning LLMs to Situated Human Values through RLHF},

author = {A. Arzberger and S. Buijsman and M. L. Lupetti and A. Bozzon and J. Yang},

url = {https://ojs.aaai.org/index.php/AIES/article/view/31617},

doi = {10.1609/aies.v7i1.31617},

issn = {3065-8365},

year  = {2024},

date = {2024-10-01},

urldate = {2024-10-01},

journal = {Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society},

volume = {7},

number = {1},

pages = {61–73},

abstract = {Work on value alignment aims to ensure that human values 

are respected by AI systems. However, existing approaches 

tend to rely on universal framings of human values that obscure 

the question of which values the systems should capture 

and align with, given the variety of operational situations. 

This often results in AI systems that privilege only a 

selected few while perpetuating problematic norms grounded 

on biases, ultimately causing equity and justice issues. In this 

perspective paper, we unpack the limitations of predominant 

alignment practices of reinforcement learning from human 

feedback (RLHF) for LLMs through the lens of situated values. 

We build on feminist epistemology to argue that at the 

design-time, RLHF has problems with representation in the 

subjects providing feedback and implicitness in the conceptualization 

of values and situations of real-world users while 

lacking system adaptation to real user situations at the use time. 

To address these shortcomings, we propose three research 

directions: 1) situated annotation to capture information 

about the crowdworker’s and user’s values and judgments 

in relation to specific situations at both the design and 

use-time, 2) expressive instruction to encode plural values 

for instructing LLMs systems at design-time, and 3) reflexive 

adaptation to leverage situational knowledge for system 

adaption at use-time. We conclude by reflecting on the 

practical challenges of pursuing these research directions and 

situated value alignment of AI more broadly.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{biswas_hi_nodate,

title = {“Hi. I’m Molly, Your Virtual Interviewer!” — Exploring the Impact of Race and Gender in AI-powered Virtual Interview Experiences},

author = {S. Biswas and J. Jung and A. Unnam and K. Yadav and S. Gupta and U. Gadiraju},

url = {https://arxiv.org/html/2408.14159v1},

year  = {2024},

date = {2024-08-26},

urldate = {2024-08-26},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{sun_revisiting_2024,

title = {Revisiting Bundle Recommendation for Intent-aware Product Bundling},

author = {Z. Sun and K. Feng and J. Yang and H. Fang and X. Qu and Y. S. Ong and W. Liu},

url = {https://dl.acm.org/doi/10.1145/3652865},

doi = {10.1145/3652865},

year  = {2024},

date = {2024-06-01},

urldate = {2024-06-01},

journal = {ACM Trans. Recomm. Syst.},

volume = {2},

number = {3},

pages = {24:1–24:34},

abstract = {Product bundling represents a prevalent marketing strategy in both offline stores and e-commerce systems. Despite its widespread use, previous studies on bundle recommendation face two significant limitations. Firstly, they rely on noisy datasets, where bundles are defined by heuristics, e.g., products co-purchased in the same session. Secondly, they target specific tasks by holding unrealistic assumptions, e.g., the availability of bundles for recommendation directly. This paper proposes to take a step back and considers the process of bundle recommendation from a holistic user experience perspective. We first construct high-quality bundle datasets with rich metadata, particularly bundle intents, through a carefully designed crowd-sourcing task. We then define a series of tasks that together, support all key steps in a typical bundle recommendation process, from bundle detection, completion and ranking, to explanation and auto-naming, whereby 19 research questions are raised correspondingly to guide the analysis. Finally, we conduct extensive experiments and analyses with representative recommendation models and large language models (LLMs), demonstrating the challenges and opportunities, especially with the emergence of LLMs. To summarize, our study contributes by introducing novel data sources, paving the way for new research avenues, and offering insights to guide product bundling in real e-commerce platforms.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{yang_fedtrans_2024,

title = {FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning},

author = {M. Yang and R. Zhu and Q. Wang and J. Yang},

url = {https://proceedings.iclr.cc/paper_files/paper/2024/hash/bb309cc1fbdb88ea755bd7cee4b310ec-Abstract-Conference.html},

year  = {2024},

date = {2024-05-01},

urldate = {2024-05-01},

journal = {International Conference on Representation Learning},

volume = {2024},

pages = {42668–42692},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{smirnova_xcrowd_2024,

title = {XCrowd: 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024},

author = {A. Smirnova and J. Yang and P. Cudre-Mauroux},

url = {http://www.scopus.com/inward/record.url?scp=85210019001&partnerID=8YFLogxK},

doi = {10.1145/3627673.3679777},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {CIKM '24},

pages = {2097–2107},

abstract = {Relation extraction methods are currently dominated by deep neural models, which capture complex statistical patterns while being brittle and vulnerable to perturbations in data and distribution. Explainability techniques offer a means for understanding such vulnerabilities, and thus represent an opportunity to mitigate future errors; yet, existing methods are limited to describing what the model 'knows', while totally failing at explaining what the model does not know. This paper presents a new method for diagnosing model predictions and detecting potential inaccuracies. Our approach involves breaking down the problem into two components: (i) determining the necessary knowledge the model should possess for accurate prediction, through human annotations, and (ii) assessing the actual knowledge possessed by the model, using explainable AI methods (XAI). We apply our method to several relation extraction tasks and conduct an empirical study leveraging human specifications of what a model should know and does not know. Results show that human workers are capable of accurately specifying the model should-knows, despite variations in the specification, that the alignment between what a model really knows and what it should know is indeed indicative of model accuracy, and that the unknowns identified through our methods allow to foresee future errors that may or may not have been observed otherwise.},

note = {Place: New York, NY 

Publisher: ACM},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{salimzadeh_when_2024,

title = {When in Doubt! Understanding the Role of Task Characteristics on Peer Decision-Making with AI Assistance: 32nd ACM Conference on User Modeling, Adaptation and Personalization},

author = {S. Salimzadeh and U. Gadiraju},

url = {http://www.scopus.com/inward/record.url?scp=85197883809&partnerID=8YFLogxK},

doi = {10.1145/3627043.3659567},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {UMAP 2024 - Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization},

pages = {89–101},

series = {UMAP 2024 - Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization},

abstract = {With the integration of AI systems into our daily lives, human-AI collaboration has become increasingly prevalent. Prior work in this realm has primarily explored the effectiveness and performance of individual human and AI systems in collaborative tasks. While much of decision-making occurs within human peers and groups in the real world, there is a limited understanding of how they collaborate with AI systems. One of the key predictors of human-AI collaboration is the characteristics of the task at hand. Understanding the influence of task characteristics on human-AI collaboration is crucial for enhancing team performance and developing effective strategies for collaboration. Addressing a research and empirical gap, we seek to explore how the features of a task impact decision-making within human-AI group settings. In a 2 × 2 between-subjects study (N = 256) we examine the effects of task complexity and uncertainty on group performance and behaviour. The participants were grouped into pairs and assigned to one of four experimental conditions characterized by varying degrees of complexity and uncertainty. We found that high task complexity and high task uncertainty can negatively impact the performance of human-AI groups, leading to decreased group accuracy and increased disagreement with the AI system. We found that higher task complexity led to a higher efficiency in decision-making, while a higher task uncertainty had a negative impact on efficiency. Our findings highlight the importance of considering task characteristics when designing human-AI collaborative systems, as well as the future design of empirical studies exploring human-AI collaboration.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{he_opening_2024,

title = {Opening the Analogical Portal to Explainability: Can Analogies Help Laypeople in AI-assisted Decision Making?},

author = {G. He and A. Balayn and S. Buijsman and J. Yang and U. Gadiraju},

url = {http://www.scopus.com/inward/record.url?scp=85204874277&partnerID=8YFLogxK},

doi = {10.1613/jair.1.15118},

issn = {1076-9757},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {Journal of Artificial Intelligence Research},

volume = {81},

pages = {117–162},

abstract = {Concepts are an important construct in semantics, based on which humans understand the world with various levels of abstraction. With the recent advances in explainable artificial intelligence (XAI), concept-level explanations are receiving an increasing amount of attention from the broad research community. However, laypeople may find such explanations difficult to digest due to the potential knowledge gap and the concomitant cognitive load. Inspired by prior work that has explored analogies and sensemaking, we argue that augmenting concept-level explanations with analogical inference information from commonsense knowledge can be a potential solution to tackle this issue. To investigate the validity of our proposition, we first designed an effective analogy-based explanation generation method and collected 600 analogy-based explanations from 100 crowd workers. Next, we proposed a set of structured dimensions for the qualitative assessment of such explanations, and conducted an empirical evaluation of the generated analogies with experts. Our findings revealed significant positive correlations between the qualitative dimensions of analogies and the perceived helpfulness of analogy-based explanations, suggesting the effectiveness of the dimensions. To understand the practical utility and the effectiveness of analogybased explanations in assisting human decision-making, we conducted a follow-up empirical study (N = 280) on a skin cancer detection task with non-expert humans and an imperfect AI system. Thus, we designed a between-subjects study spanning five different experimental conditions with varying types of explanations. The results of our study confirmed that a knowledge gap can prevent participants from understanding concept-level explanations. Consequently, when only the target domain of our designed analogy-based explanation was provided (in a specific experimental condition), participants demonstrated relatively more appropriate reliance on the AI system. In contrast to our expectations, we found that analogies were not effective in fostering appropriate reliance. We carried out a qualitative analysis of the open-ended responses from participants in the study regarding their perceived usefulness of explanations and analogies. Our findings suggest that human intuition and the perceived plausibility of analogies may have played a role in affecting user reliance on the AI system. We also found that the understanding of commonsense explanations varied with the varying experience of the recipient user, which points out the need for further work on personalization when leveraging commonsense explanations. In summary, although we did not find quantitative support for our hypotheses around the benefits of using analogies, we found considerable qualitative evidence suggesting the potential of high-quality analogies in aiding non-expert users in their decision making with AI-assistance. These insights can inform the design of future methods for the generation and use of effective analogy-based explanations.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{corti_it_2024,

title = {“It Is a Moving Process”: 2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024},

author = {L. Corti and R. Oltmans and J. Jung and A. Balayn and M. Wijsenbeek and J. Yang},

editor = {F. Mueller and P. Kyburz and J. R. Williamson and C. Sas and M. L. Wilson and P. Toups Dugas and I. Shklovski},

url = {http://www.scopus.com/inward/record.url?scp=85194835253&partnerID=8YFLogxK},

doi = {10.1145/3613904.3642551},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems},

abstract = {Clinicians increasingly pay attention to Artificial Intelligence (AI) to improve the quality and timeliness of their services. There are converging opinions on the need for Explainable AI (XAI) in healthcare. However, prior work considers explanations as stationary entities with no account for the temporal dynamics of patient care. In this work, we involve 16 Idiopathic Pulmonary Fibrosis (IPF) clinicians from a European university medical centre and investigate their evolving uses and purposes for explainability throughout patient care. By applying a patient journey map for IPF, we elucidate clinicians' informational needs, how human agency and patient-specific conditions can influence the interaction with XAI systems, and the content, delivery, and relevance of explanations over time. We discuss implications for integrating XAI in clinical contexts and more broadly how explainability is defined and evaluated. Furthermore, we reflect on the role of medical education in addressing epistemic challenges related to AI literacy.},

note = {Publisher: ACM},

keywords = {},

pubstate = {published},

tppubtype = {article}

}