Information Access in the Era of Generative AI

Information access systems, especially search engines and recommender systems, play a vital role in the access to information that is crucial for decision-making and action in the world. The emergence of Generative Artificial Intelligence (GenAI) has led to more advanced user experiences in these systems with natural user-system interactions and auto-generated answers and suggestions, potentially saving people time and cognitive effort, while improving task outcomes. This chapter explores the synergies between GenAI and information access and provides a framing for the rest of the book. GenAI technologies, such as transformers and large language models, have revolutionized various fields, including creative writing, software development, and multimodal content generation. We briefly discuss ongoing GenAI-related research in search and recommendation that is exploring areas such as generative document retrieval, grounded answer generation, generative recommendation, and generative knowledge graphs, enhancing the capabilities of information systems. We also cover other topics such as combining information interaction modalities (e.g., data types, interaction paradigms) in different ways to create unified, so-called “panmodal” GenAI-powered information experiences that leverage the strengths of different interaction modes and highlight the growing interest and collaboration in GenAI and its applications in information access. We conclude by discussing the ethical considerations and challenges that come from the rise of this new technology, emphasizing the need for responsible development and deployment to harness its potential while mitigating risks.

The chapter discusses the foundational impact of modern generative Artificial Intelligence (AI) models on Information Access (IA) systems. In contrast to traditional AI, the large-scale training and superior data modeling of generative AI models enable them to produce high-quality, human-like responses, which bring brand new opportunities for the development of IA paradigms. In this chapter, we identify and introduce two of them in detail, i.e., information generation and information synthesis. Information generation allows AI to create tailored content addressing user needs directly, enhancing user experience with immediate, relevant outputs. Information synthesis leverages the ability of generative AI to integrate and reorganize existing information, providing grounded responses and mitigating issues like model hallucination, which is particularly valuable in scenarios requiring precision and external knowledge. This chapter delves into the foundational aspects of generative models, including architecture, scaling, and training, and discusses their applications in multi-modal scenarios. Additionally, it examines the retrieval-augmented generation paradigm and other methods for corpus modeling and understanding, demonstrating how generative AI can enhance information access systems. It also summarizes potential challenges and fruitful directions for future studies.

Recent advancements in generative artificial intelligence have provided unique opportunities for seamless information access and discovery, particularly through natural language interactions. These technologies enable users to easily describe their needs and provide interactive feedback. This chapter provides an overview of the opportunities and challenges in interacting with information access systems powered by generative artificial intelligence technologies. We focus on user interfaces in these systems and various interactions for describing and clarifying users’ needs, refining the result list produced by the system, providing proactive feedback to the system, the system proactively initiating conversations, explaining the result list, and enabling multi-modal interactions for information access.

Generative Information Retrieval (GenIR) signifies an advancement in Information Retrieval (IR). GenIR encourages more sophisticated, conversational responses to search queries by integrating generative models and chat-like interfaces. However, this approach retains core principles of traditional IR and conversational information seeking, illustrating its capacity to augment current IR frameworks.

In this chapter, we propose that introducing GenIR enhances traditional information retrieval tasks and expands their scope. This allows systems to manage more complex queries, including generative, critiquing, and extractive tasks. These advancements surpass traditional systems, handling queries with greater depth and flexibility. This sometimes-speculative chapter suggests Generative Information Access (GenIA), a term that more accurately encapsulates the widened scope and enhanced functionalities of GenIR, particularly in how this relates to tasks. By investigating the impact of GenIR, this discussion aims to reiterate that generative research should not abandon traditional interactive information retrieval research but rather incorporate it into future research and development efforts.

In this chapter, we discuss how to improve Generative Information Retrieval (GenIR) systems based on user feedback. Before describing the approaches, it is necessary to be aware that the concept of “user” has been extended in the interactions with the GenIR systems. Different types of feedback information and strategies are also provided. Then the alignment techniques are highlighted in terms of objectives and methods. Following this, various ways of learning from user feedback in GenIR are presented, including continual learning, learning and ranking in the conversational context, and prompt learning. Through this comprehensive exploration, it becomes evident that innovative techniques are being proposed beyond traditional methods of utilizing user feedback and contribute significantly to the evolution of GenIR in the new era. We also summarize some challenging topics and future directions that require further investigation.

In this chapter, we consider generative information retrieval (IR) evaluation from two distinct but interrelated perspectives. First, Large Language Models (LLMs) themselves are rapidly becoming tools for evaluation, with current research indicating that LLMs may be superior to crowdsource workers and other paid assessors on basic relevance judgment tasks. We review past and ongoing related research, including speculation on the future of shared task initiatives, such as the Text Retrieval Conference (TREC), and a discussion on the continuing need for human assessments. Second, we consider the evaluation of emerging LLM-based Generative Information Retrieval (GenIR) systems, including Retrieval-Augmented Generation (RAG) systems. We consider approaches that focus both on the end-to-end evaluation of GenIR systems and on the evaluation of a retrieval component as an element in a RAG system. Going forward, we expect the evaluation of GenIR systems to be at least partially based on LLM-based assessment, creating an apparent circularity, with a system seemingly evaluating its own output. We resolve this apparent circularity in two ways: (1) by viewing LLM-based assessment as a form of “slow search,” where a slower IR system is used for evaluation and training of a faster production IR system, and (2) by recognizing the continuing need to ground evaluation in human assessment, even if the characteristics of that human assessment must change.

Robust access to trustworthy information is a critical need for society with implications for knowledge production, public health education, and promoting informed citizenry in democratic societies. Generative AI technologies may enable new ways to access information and improve effectiveness of existing information retrieval systems, but we are only starting to understand and grapple with their long-term social implications. In this chapter, we present an overview of some of the systemic consequences and risks of employing generative AI in the context of information access. We also provide recommendations for evaluation and mitigation and discuss challenges for future research.

The landscape of recommendation systems has undergone significant transformation, driven by advancements in generative AI. This section explores how generative AI, particularly Large Language Models (LLMs), can revolutionize traditional recommendation systems. By leveraging their powerful capabilities in language comprehension, reasoning, planning, and generation, recommendation systems can facilitate more intelligent user-system interactions, enhance personalized content generation, improve data representation, achieve generative item recall and ranking, and contribute to evaluation processes. These advancements promise to enhance user experience and system performance but also present challenges such as ensuring trustworthiness in AI-generated content and managing high computational costs. We discuss these developments and identify open problems and future research directions for integrating generative AI into recommendation systems.

Generative Artificial Intelligence (AI) offers powerful tools that fundamentally change the design of information access systems; however, it is unclear how to use them to best serve the needs of people. At present, Large Language Models (LLMs) process natural language (and multi-modal) input and present credible-appearing but often completely untrue multi-modal output. This opens the door to research into how to produce true, complete, relevant information, where and how to design retrieval augmentation to personalize and ground the system, and how to evaluate beyond relevance for truth, completeness, utility, and satisfaction. The applications of generative AI for information-seeking tasks are broad. In this chapter, we present recent developments in four domains that have been well studied in the information retrieval community (education, biomedical, legal, and finance). We follow with a discussion of new challenges (agentic systems) and research areas that are common to most applications of generative AI to information seeking tasks (credibility and veracity, new paradigms for evaluation, and synthetic data generation). The field of Information Retrieval (IR) is at the leading edge of a transformation in how people access information and accomplish tasks. We have the rare opportunity to design and build the future we want to live in.