Large Language Model Driven Recommendation

While previous chapters focused on recommendation systems (RSs) based on standardized, non-verbal user feedback such as purchases, views, and clicks -- the advent of LLMs has unlocked the use of natural language (NL) interactions for recommendation. This chapter discusses how LLMs' abilities for general NL reasoning present novel opportunities to build highly personalized RSs -- which can effectively connect nuanced and diverse user preferences to items, potentially via interactive dialogues. To begin this discussion, we first present a taxonomy of the key data sources for language-driven recommendation, covering item descriptions, user-system interactions, and user profiles. We then proceed to fundamental techniques for LLM recommendation, reviewing the use of encoder-only and autoregressive LLM recommendation in both tuned and untuned settings. Afterwards, we move to multi-module recommendation architectures in which LLMs interact with components such as retrievers and RSs in multi-stage pipelines. This brings us to architectures for conversational recommender systems (CRSs), in which LLMs facilitate multi-turn dialogues where each turn presents an opportunity not only to make recommendations, but also to engage with the user in interactive preference elicitation, critiquing, and question-answering.

XAI4LLM. Let Machine Learning Models and LLMs Collaborate for Enhanced In-Context Learning in Healthcare

The integration of Large Language Models (LLMs) into healthcare diagnostics offers a promising avenue for clinical decision-making. This study outlines the development of a novel method for zero-shot/few-shot in-context learning (ICL) by integrating medical domain knowledge using a multi-layered structured prompt. We also explore the efficacy of two communication styles between the user and LLMs: the Numerical Conversational (NC) style, which processes data incrementally, and the Natural Language Single-Turn (NL-ST) style, which employs long narrative prompts. Our study systematically evaluates the diagnostic accuracy and risk factors, including gender bias and false negative rates, using a dataset of 920 patient records in various few-shot scenarios. Results indicate that traditional clinical machine learning (ML) models generally outperform LLMs in zero-shot and few-shot settings. However, the performance gap narrows significantly when employing few-shot examples alongside effective explainable AI (XAI) methods as sources of domain knowledge. Moreover, with sufficient time and an increased number of examples, the conversational style (NC) nearly matches the performance of ML models. Most notably, LLMs demonstrate comparable or superior cost-sensitive accuracy relative to ML models. This research confirms that, with appropriate domain knowledge and tailored communication strategies, LLMs can significantly enhance diagnostic processes. The findings highlight the importance of optimizing the number of training examples and communication styles to improve accuracy and reduce biases in LLM applications.

FairEvalLLM. A Comprehensive Framework for Benchmarking Fairness in Large Language Model Recommender Systems

This paper presents a framework for evaluating fairness in recommender systems powered by Large Language Models (RecLLMs), addressing the need for a unified approach that spans various fairness dimensions including sensitivity to user attributes, intrinsic fairness, and discussions of fairness based on underlying benefits. In addition, our framework introduces counterfactual evaluations and integrates diverse user group considerations to enhance the discourse on fairness evaluation for RecLLMs. Our key contributions include the development of a robust framework for fairness evaluation in LLM-based recommendations and a structured method to create \textit{informative user profiles} from demographic data, historical user preferences, and recent interactions. We argue that the latter is essential for enhancing personalization in such systems, especially in temporal-driven scenarios. We demonstrate the utility of our framework through practical applications on two datasets, LastFM-1K and ML-1M. We conduct experiments on a subsample of 80 users from each dataset, testing and assessing the effectiveness of various prompt construction scenarios and in-context learning, comprising more than 50 scenarios. This results in more than 4000 recommendations (80 * 50 = 4000). Our study reveals that while there are no significant unfairness issues in scenarios involving sensitive attributes, some concerns remain. However, in terms of intrinsic fairness, which does not involve direct sensitivity, unfairness across demographic groups remains significant. The code and data used for this paper are available at: \url{https://shorturl.at/awBFM}.

Understanding Language Modeling Paradigm Adaptations in Recommender Systems: Lessons Learned and Open Challenges

The emergence of Large Language Models (LLMs) has achieved tremendous success in the field of Natural Language Processing owing to diverse training paradigms that empower LLMs to effectively capture intricate linguistic patterns and semantic representations. In particular, the recent "pre-train, prompt and predict" training paradigm has attracted significant attention as an approach for learning generalizable models with limited labeled data. In line with this advancement, these training paradigms have recently been adapted to the recommendation domain and are seen as a promising direction in both academia and industry. This half-day tutorial aims to provide a thorough understanding of extracting and transferring knowledge from pre-trained models learned through different training paradigms to improve recommender systems from various perspectives, such as generality, sparsity, effectiveness and trustworthiness. In this tutorial, we first introduce the basic concepts and a generic architecture of the language modeling paradigm for recommendation purposes. Then, we focus on recent advancements in adapting LLM-related training strategies and optimization objectives for different recommendation tasks. After that, we will systematically introduce ethical issues in LLM-based recommender systems and discuss possible approaches to assessing and mitigating them. We will also summarize the relevant datasets, evaluation metrics, and an empirical study on the recommendation performance of training paradigms. Finally, we will conclude the tutorial with a discussion of open challenges and future directions.

A Review of Modern Recommender Systems Using Generative Models

Traditional recommender systems (RS) have used user-item rating histories as their primary data source, with collaborative filtering being one of the principal methods. However, generative models have recently developed abilities to model and sample from complex data distributions, including not only user-item interaction histories but also text, images, and videos - unlocking this rich data for novel recommendation tasks. Through this comprehensive and multi-disciplinary survey, we aim to connect the key advancements in RS using Generative Models (Gen-RecSys), encompassing: a foundational overview of interaction-driven generative models; the application of large language models (LLM) for generative recommendation, retrieval, and conversational recommendation; and the integration of multimodal models for processing and generating image and video content in RS. Our holistic perspective allows us to highlight necessary paradigms for evaluating the impact and harm of Gen-RecSys and identify open challenges. A more up-to-date version of the papers is maintained at: https://github.com/yasdel/LLM-RecSys.

CFaiRLLM: Consumer Fairness Evaluation in Large-Language Model Recommender System

In the evolving landscape of recommender systems, the integration of Large Language Models (LLMs) such as ChatGPT marks a new era, introducing the concept of Recommendation via LLM (RecLLM). While these advancements promise unprecedented personalization and efficiency, they also bring to the fore critical concerns regarding fairness, particularly in how recommendations might inadvertently perpetuate or amplify biases associated with sensitive user attributes. In order to address these concerns, our study introduces a comprehensive evaluation framework, CFaiRLLM, aimed at evaluating (and thereby mitigating) biases on the consumer side within RecLLMs. Our research methodically assesses the fairness of RecLLMs by examining how recommendations might vary with the inclusion of sensitive attributes such as gender, age, and their intersections, through both similarity alignment and true preference alignment. By analyzing recommendations generated under different conditions-including the use of sensitive attributes in user prompts-our framework identifies potential biases in the recommendations provided. A key part of our study involves exploring how different detailed strategies for constructing user profiles (random, top-rated, recent) impact the alignment between recommendations made without consideration of sensitive attributes and those that are sensitive-attribute-aware, highlighting the bias mechanisms within RecLLMs. The findings in our study highlight notable disparities in the fairness of recommendations, particularly when sensitive attributes are integrated into the recommendation process, either individually or in combination. The analysis demonstrates that the choice of user profile sampling strategy plays a significant role in affecting fairness outcomes, highlighting the complexity of achieving fair recommendations in the era of LLMs.

A Personalized Framework for Consumer and Producer Group Fairness Optimization in Recommender Systems

In recent years, there has been an increasing recognition that when machine learning (ML) algorithms are used to automate decisions, they may mistreat individuals or groups, with legal, ethical, or economic implications. Recommender systems are prominent examples of these machine learning (ML) systems that aid users in making decisions. The majority of past literature research on RS fairness treats user and item fairness concerns independently, ignoring the fact that recommender systems function in a two-sided marketplace. In this paper, we propose CP-FairRank, an optimization-based re-ranking algorithm that seamlessly integrates fairness constraints from both the consumer and producer side in a joint objective framework. The framework is generalizable and may take into account varied fairness settings based on group segmentation, recommendation model selection, and domain, which is one of its key characteristics. For instance, we demonstrate that the system may jointly increase consumer and producer fairness when (un)protected consumer groups are defined on the basis of their activity level and main-streamness, while producer groups are defined according to their popularity level. For empirical validation, through large-scale on eight datasets and four mainstream collaborative filtering (CF) recommendation models, we demonstrate that our proposed strategy is able to improve both consumer and producer fairness without compromising or very little overall recommendation quality, demonstrating the role algorithms may play in avoiding data biases.

Understanding Biases in ChatGPT-based Recommender Systems: Provider Fairness, Temporal Stability, and Recency

This study explores the nuanced capabilities and inherent biases of Recommender Systems using Large Language Models (RecLLMs), with a focus on ChatGPT-based systems. It studies into the contrasting behaviors of generative models and traditional collaborative filtering models in movie recommendations. The research primarily investigates prompt design strategies and their impact on various aspects of recommendation quality, including accuracy, provider fairness, diversity, stability, genre dominance, and temporal freshness (recency). Our experimental analysis reveals that the introduction of specific 'system roles' and 'prompt strategies' in RecLLMs significantly influences their performance. For instance, role-based prompts enhance fairness and diversity in recommendations, mitigating popularity bias. We find that while GPT-based models do not always match the performance of CF baselines, they exhibit a unique tendency to recommend newer and more diverse movie genres. Notably, GPT-based models tend to recommend more recent films, particularly those released post-2000, and show a preference for genres like \sq{Drama} and Comedy, and Romance (compared to CF Action, Adventure) presumably due to the RecLLMs' training on varied data sets, which allows them to capture recent trends and discussions more effectively than CF models. Interestingly, our results demonstrate that the 'Simple' and 'Chain of Thought (COT)' paradigms yield the highest accuracy. These findings imply the potential of combining these strategies with scenarios that favor more recent content, thereby offering a more balanced and up-to-date recommendation experience. This study contributes significantly to the understanding of emerging RecLLMs, particularly in the context of harms and biases within these systems.

Fairness for All: Investigating Harms to Within-Group Individuals in Producer Fairness Re-ranking Optimization -- A Reproducibility Study

Recommender systems are widely used to provide personalized recommendations to users. Recent research has shown that recommender systems may be subject to different types of biases, such as popularity bias, leading to an uneven distribution of recommendation exposure among producer groups. To mitigate this, producer-centered fairness re-ranking (PFR) approaches have been proposed to ensure equitable recommendation utility across groups. However, these approaches overlook the harm they may cause to within-group individuals associated with colder items, which are items with few or no interactions. This study reproduces previous PFR approaches and shows that they significantly harm colder items, leading to a fairness gap for these items in both advantaged and disadvantaged groups. Surprisingly, the unfair base recommendation models were providing greater exposure opportunities to these individual cold items, even though at the group level, they appeared to be unfair. To address this issue, the study proposes an amendment to the PFR approach that regulates the number of colder items recommended by the system. This modification achieves a balance between accuracy and producer fairness while optimizing the selection of colder items within each group, thereby preventing or reducing harm to within-group individuals and augmenting the novelty of all recommended items. The proposed method is able to register an increase in sub-group fairness (SGF) from 0.3104 to 0.3782, 0.6156, and 0.9442 while also improving group-level fairness (GF) (112% and 37% with respect to base models and traditional PFR). Moreover, the proposed method achieves these improvements with minimal or no reduction in accuracy (or even an increase sometimes). We evaluate the proposed method on various recommendation datasets and demonstrate promising results independent of the underlying model or datasets.

ChatGPT-HealthPrompt. Harnessing the Power of XAI in Prompt-Based Healthcare Decision Support using ChatGPT

This study presents an innovative approach to the application of large language models (LLMs) in clinical decision-making, focusing on OpenAI's ChatGPT. Our approach introduces the use of contextual prompts-strategically designed to include task description, feature description, and crucially, integration of domain knowledge-for high-quality binary classification tasks even in data-scarce scenarios. The novelty of our work lies in the utilization of domain knowledge, obtained from high-performing interpretable ML models, and its seamless incorporation into prompt design. By viewing these ML models as medical experts, we extract key insights on feature importance to aid in decision-making processes. This interplay of domain knowledge and AI holds significant promise in creating a more insightful diagnostic tool. Additionally, our research explores the dynamics of zero-shot and few-shot prompt learning based on LLMs. By comparing the performance of OpenAI's ChatGPT with traditional supervised ML models in different data conditions, we aim to provide insights into the effectiveness of prompt engineering strategies under varied data availability. In essence, this paper bridges the gap between AI and healthcare, proposing a novel methodology for LLMs application in clinical decision support systems. It highlights the transformative potential of effective prompt design, domain knowledge integration, and flexible learning approaches in enhancing automated decision-making.