Information retrieval systems aim to return relevant and useful content to users and are often biased towards popular items. This implies that an under-represented group or attribute will not receive a fair share of a user’s attention in search results. For example, while a ranked results list for a query such as ‘physicists’ might be fair according to a particular attribute such as gender, nationality or social group, it might not be fair for all of them. Ideally, while providing relevant answers, a results list should also provide fair exposure across a broad range of attributes. We demonstrate that while a system can be fair towards multiple attributes, they are not necessarily diverse (i.e., redundancy/minimal novelty). To this end, we include an additional dimension to the study, i.e., diversity, and explore the relationship between fairness and diversity measures by exploring popular search result diversification techniques using the test collections from TREC 2021 Fair Ranking Track, TREC 2022 Fair Ranking Track and NTCIR-17 FairWeb-1. Furthermore, we study the impact of such diversification techniques along both nominal and ordinal attributes, as well as for intersectional fairness. Our results indicate that explicit search results diversification techniques showed improved results when the attributes were nominal but failed to provide fairer and more diverse results when the attributes were ordinal in nature. Additionally, in terms of intersectional fairness explicit search results diversification also performed significantly better than baseline retrieval runs.

Social media platforms must filter sexist content in compliance with governmental regulations. Current machine learning approaches can reliably detect sexism based on standardized definitions, but often neglect the subjective nature of sexist language and fail to consider individual users' perspectives. To address this gap, we adopt a perspectivist approach, retaining diverse annotations rather than enforcing gold-standard labels or their aggregations, allowing models to account for personal or group-specific views of sexism. Using demographic data from Twitter, we employ large language models (LLMs) to personalize the identification of sexism.

Creating and deploying customized applications is crucial for operational success and enriching user experiences in the rapidly evolving modern business world. A prominent facet of modern user experiences is the integration of chatbots or voice assistants. The rapid evolution of Large Language Models (LLMs) has provided a powerful tool to build conversational applications. We present Walert, a customized LLM-based conversational agent able to answer frequently asked questions about computer science degrees and programs at RMIT University. Our demo aims to showcase how conversational information-seeking researchers can effectively communicate the benefits of using best practices to stakeholders interested in developing and deploying LLM-based chatbots. These practices are well-known in our community but often overlooked by practitioners who may not have access to this knowledge. The methodology and resources used in this demo serve as a bridge to facilitate knowledge transfer from experts, address industry professionals’ practical needs, and foster a collaborative environment. The data and code of the demo are available at https://github.com/rmit-ir/walert.

Conversational intelligent assistants, such as Amazon Alexa, Google Assistant, and Apple Siri, are a form of voice-only Question Answering (QA) system and have the potential to address complex information needs. However, at the moment they are mostly limited to answering with facts expressed in a few words. For example, when a user asks Google Assistant if coffee is good for their health, it responds by justifying why it is good for their health without shedding any light on the side effects coffee consumption might have \citegao2020toward. Such limited exposure to multiple perspectives can lead to change in perceptions, preferences, and attitude of users, as well as to the creation and reinforcement of undesired cognitive biases. Getting such QA systems to provide a fair exposure to complex answers -- including those with opposing perspectives -- is an open research problem. In this research, I aim to address the problem of fairly exposing multiple perspectives and relevant answers to users in a multi-turn conversation without negatively impacting user satisfaction.

Existing commercial search engines often struggle to represent different perspectives of a search query. Argument retrieval systems address this limitation of search engines and provide both positive (PRO) and negative (CON) perspectives about a user's information need on a controversial topic (e.g., climate change). The effectiveness of such argument retrieval systems is typically evaluated based on topical relevance and argument quality, without taking into account the often differing number of documents shown for the argument stances (PRO or CON). Therefore, systems may retrieve relevant passages, but with a biased exposure of arguments. In this work, we analyze a range of non-stochastic fairness-aware ranking and diversity metrics to evaluate the extent to which argument stances are fairly exposed in argument retrieval systems.