Large Language Models (LLMs) have empowered AI agents with advanced capabilities for understanding, reasoning, and interacting across diverse tasks. The addition of memory further enhances them by enabling continuity across interactions, learning from past experiences, and improving the relevance of actions and responses over time; termed as memory-enhanced personalization. Although such personalization through memory offers clear benefits, it also introduces risks of bias. While several previous studies have highlighted bias in ML and LLMs, bias due to memory-enhanced personalized agents is largely unexplored. Using recruitment as an example use case, we simulate the behavior of a memory-enhanced personalized agent, and study whether and how bias is introduced and amplified in and across various stages of operation. Our experiments on agents using safety-trained LLMs reveal that bias is systematically introduced and reinforced through personalization, emphasizing the need for additional protective measures or agent guardrails in memory-enhanced LLM-based AI agents.

The absence of explicitly tailored, accessible annotated datasets for educational purposes presents a notable obstacle for NLP tasks in languages with limited resources. This study initially explores the feasibility of using machine translation (MT) to convert an existing dataset into a Tigrinya dataset in SQuAD format. As a result, we present TIGQA, an expert-annotated dataset containing 2,685 question-answer pairs covering 122 diverse topics such as climate, water, and traffic. These pairs are from 537 context paragraphs in publicly accessible Tigrinya and Biology books. Through comprehensive analyses, we demonstrate that the TIGQA dataset requires skills beyond simple word matching, requiring both single-sentence and multiple-sentence inference abilities. We conduct experiments using state-of-the-art MRC methods, marking the first exploration of such models on TIGQA. Additionally, we estimate human performance on the dataset and juxtapose it with the results obtained from pre-trained models. The notable disparities between human performance and the best model performance underscore the potential for fu- ture enhancements to TIGQA through continued research. Our dataset is freely accessible via the provided link to encourage the research community to address the challenges in the Tigrinya MRC. Keywords: Tigrinya QA dataset, Low resource QA dataset, domain specific QA

With increasing digitalization, Artificial Intelligence (AI) is becoming ubiquitous. AI-based systems to identify, optimize, automate, and scale solutions to complex economic and societal problems are being proposed and implemented. This has motivated regulation efforts, including the Proposal of an EU AI Act. This interdisciplinary position paper considers various concerns surrounding fairness and discrimination in AI, and discusses how AI regulations address them, focusing on (but not limited to) the Proposal. We first look at AI and fairness through the lenses of law, (AI) industry, sociotechnology, and (moral) philosophy, and present various perspectives. Then, we map these perspectives along three axes of interests: (i) Standardization vs. Localization, (ii) Utilitarianism vs. Egalitarianism, and (iii) Consequential vs. Deontological ethics which leads us to identify a pattern of common arguments and tensions between these axes. Positioning the discussion within the axes of interest and with a focus on reconciling the key tensions, we identify and propose the roles AI Regulation should take to make the endeavor of the AI Act a success in terms of AI fairness concerns.

Recently, almost all conferences have moved to virtual mode due to the pandemic-induced restrictions on travel and social gathering. Contrary to in-person conferences, virtual conferences face the challenge of efficiently scheduling talks, accounting for the availability of participants from different timezones and their interests in attending different talks. A natural objective for conference organizers is to maximize efficiency, e.g., total expected audience participation across all talks. However, we show that optimizing for efficiency alone can result in an unfair virtual conference schedule, where individual utilities for participants and speakers can be highly unequal. To address this, we formally define fairness notions for participants and speakers, and derive suitable objectives to account for them. As the efficiency and fairness objectives can be in conflict with each other, we propose a joint optimization framework that allows conference organizers to design schedules that balance (i.e., allow trade-offs) among efficiency, participant fairness and speaker fairness objectives. While the optimization problem can be solved using integer programming to schedule smaller conferences, we provide two scalable techniques to cater to bigger conferences. Extensive evaluations over multiple real-world datasets show the efficacy and flexibility of our proposed approaches.

Many online platforms today (such as Amazon, Netflix, Spotify, LinkedIn, and AirBnB) can be thought of as two-sided markets with producers and customers of goods and services. Traditionally, recommendation services in these platforms have focused on maximizing customer satisfaction by tailoring the results according to the personalized preferences of individual customers. However, our investigation reinforces the fact that such customer-centric design of these services may lead to unfair distribution of exposure to the producers, which may adversely impact their well-being. However, a pure producer-centric design might become unfair to the customers. As more and more people are depending on such platforms to earn a living, it is important to ensure fairness to both producers and customers. In this work, by mapping a fair personalized recommendation problem to a constrained version of the problem of fairly allocating indivisible goods, we propose to provide fairness guarantees for both sides. Formally, our proposed FairRec algorithm guarantees Maxi-Min Share of exposure for the producers, and Envy-Free up to One Item fairness for the customers. Extensive evaluations over multiple real-world datasets show the effectiveness of FairRec in ensuring two-sided fairness while incurring a marginal loss in overall recommendation quality. Finally, we present a modification of FairRec (named as FairRecPlus ) that at the cost of additional computation time, improves the recommendation performance for the customers, while maintaining the same fairness guarantees.

Recommender systems are one of the most widely used services on several online platforms to suggest potential items to the end-users. These services often use different machine learning techniques for which fairness is a concerning factor, especially when the downstream services have the ability to cause social ramifications. Thus, focusing on the non-personalised (global) recommendations in news media platforms (e.g., top-k trending topics on Twitter, top-k news on a news platform, etc.), we discuss on two specific fairness concerns together (traditionally studied separately)---user fairness and organisational fairness. While user fairness captures the idea of representing the choices of all the individual users in the case of global recommendations, organisational fairness tries to ensure politically/ideologically balanced recommendation sets. This makes user fairness a user-side requirement and organisational fairness a platform-side requirement. For user fairness, we test with methods from social choice theory, i.e., various voting rules known to better represent user choices in their results. Even in our application of voting rules to the recommendation setup, we observe high user satisfaction scores. Now for organisational fairness, we propose a bias metric which measures the aggregate ideological bias of a recommended set of items (articles). Analysing the results obtained from voting rule-based recommendation, we find that while the well-known voting rules are better from the user side, they show high bias values and clearly not suitable for organisational requirements of the platforms. Thus, there is a need to build an encompassing mechanism by cohesively bridging ideas of user fairness and organisational fairness. In this abstract paper, we intend to frame the elementary ideas along with the clear motivation behind the requirement of such a mechanism.

Major online platforms today can be thought of as two-sided markets with producers and customers of goods and services. There have been concerns that over-emphasis on customer satisfaction by the platforms may affect the well-being of the producers. To counter such issues, few recent works have attempted to incorporate fairness for the producers. However, these studies have overlooked an important issue in such platforms -- to supposedly improve customer utility, the underlying algorithms are frequently updated, causing abrupt changes in the exposure of producers. In this work, we focus on the fairness issues arising out of such frequent updates, and argue for incremental updates of the platform algorithms so that the producers have enough time to adjust (both logistically and mentally) to the change. However, naive incremental updates may become unfair to the customers. Thus focusing on recommendations deployed on two-sided platforms, we formulate an ILP based online optimization to deploy changes incrementally in η steps, where we can ensure smooth transition of the exposure of items while guaranteeing a minimum utility for every customer. Evaluations over multiple real world datasets show that our proposed mechanism for platform updates can be efficient and fair to both the producers and the customers in two-sided platforms.

The proliferation of smartphones has led to the increased popularity of location-based search and recommendation systems. Online platforms like Google and Yelp allow location-based search in the form of a nearby feature to query for hotels or restaurants in the vicinity. Moreover, hotel booking platforms like Booking[dot]com, Expedia, or Trivago allow travelers searching for accommodations using either their desired location as a search query or near a particular landmark. Since the popularity of different locations in a city varies, certain locations may get more queries than other locations. Thus, the exposure received by different establishments at these locations may be very different from their intrinsic quality as captured in their ratings.Today, many small businesses (shops, hotels, or restaurants) rely on such online platforms for attracting customers. Thus, receiving less exposure than what is expected can be unfavorable for businesses. It could have a negative impact on their revenue and potentially lead to economic starvation or even shutdown. By gathering and analyzing data from three popular platforms, we observe that many top-rated hotels and restaurants get less exposure vis-a-vis their quality, which could be detrimental for them. Following a meritocratic notion, we define and quantify such exposure disparity due to location-based searches on these platforms. We attribute this exposure disparity mainly to two kinds of biases - Popularity Bias and Position Bias. Our experimental evaluation on multiple datasets reveals that although the platforms are doing well in delivering distance-based results, exposure disparity exists for individual businesses and needs to be reduced for business sustainability.

The COVID-19 pandemic has made it paramount to maintain social distance to limit the viral transmission probability. At the same time, local businesses (e.g., restaurants, cafes, stores, malls) need to operate to ensure their economic sustainability. Considering the wide usage of local recommendation platforms like Google Local and Yelp by customers to choose local businesses, we propose to design local recommendation systems which can help in achieving both safety and sustainability goals. Our investigation of existing local recommendation systems shows that they can lead to overcrowding at some businesses compromising customer safety, and very low footfall at other places threatening their economic sustainability. On the other hand, naive ways of ensuring safety and sustainability can cause significant loss in recommendation utility for the customers. Thus, we formally express the problem as a multi-objective optimization problem and solve by innovatively mapping it to a bipartite matching problem with polynomial time solutions. Extensive experiments over multiple real-world datasets reveal the efficacy of our approach along with the three-way control over sustainability, safety, and utility goals.

We investigate the problem of fair recommendation in the context of two-sided online platforms, comprising customers on one side and producers on the other. Traditionally, recommendation services in these platforms have focused on maximizing customer satisfaction by tailoring the results according to the personalized preferences of individual customers. However, our investigation reveals that such customer-centric design may lead to unfair distribution of exposure among the producers, which may adversely impact their well-being. On the other hand, a producer-centric design might become unfair to the customers. Thus, we consider fairness issues that span both customers and producers. Our approach involves a novel mapping of the fair recommendation problem to a constrained version of the problem of fairly allocating indivisible goods. Our proposed FairRec algorithm guarantees at least Maximin Share (MMS) of exposure for most of the producers and Envy-Free up to One Good (EF1) fairness for every customer. Extensive evaluations over multiple real-world datasets show the effectiveness of FairRec in ensuring two-sided fairness while incurring a marginal loss in the overall recommendation quality.