Search Still Matters: Information Retrieval in the Era of Generative AI
- URL: http://arxiv.org/abs/2311.18550v2
- Date: Sun, 17 Dec 2023 18:57:21 GMT
- Title: Search Still Matters: Information Retrieval in the Era of Generative AI
- Authors: William R. Hersh
- Abstract summary: This perspective explores the use of generative AI in the context of the motivations, considerations, and outcomes of the IR process.
Users of such systems, particularly academics, have concerns for authoritativeness, timeliness, and contextualization of search.
- Score: 1.68609633200389
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Objective: Information retrieval (IR, also known as search) systems are
ubiquitous in modern times. How does the emergence of generative artificial
intelligence (AI), based on large language models (LLMs), fit into the IR
process? Process: This perspective explores the use of generative AI in the
context of the motivations, considerations, and outcomes of the IR process with
a focus on the academic use of such systems. Conclusions: There are many
information needs, from simple to complex, that motivate use of IR. Users of
such systems, particularly academics, have concerns for authoritativeness,
timeliness, and contextualization of search. While LLMs may provide
functionality that aids the IR process, the continued need for search systems,
and research into their improvement, remains essential.
Related papers
- DynaSearcher: Dynamic Knowledge Graph Augmented Search Agent via Multi-Reward Reinforcement Learning [4.817888539036794]
DynaSearcher is an innovative search agent enhanced by dynamic knowledge graphs and multi-reward reinforcement learning (RL)<n>We employ a multi-reward RL framework for fine-grained control over training objectives such as retrieval accuracy, efficiency, and response quality.<n> Experimental results demonstrate that our approach achieves state-of-the-art answer accuracy on six multi-hop question answering datasets.
arXiv Detail & Related papers (2025-07-23T09:58:31Z) - From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents [96.65646344634524]
Large Language Models (LLMs), endowed with reasoning and agentic capabilities, are ushering in a new paradigm termed Agentic Deep Research.<n>We trace the evolution from static web search to interactive, agent-based systems that plan, explore, and learn.<n>We demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking.
arXiv Detail & Related papers (2025-06-23T17:27:19Z) - R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning [83.256752220849]
Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge.<n>We introduce R1-Searcher++, a framework designed to train LLMs to adaptively leverage both internal and external knowledge sources.<n>Our experiments demonstrate that R1-Searcher++ outperforms previous RAG and reasoning methods and achieves efficient retrieval.
arXiv Detail & Related papers (2025-05-22T17:58:26Z) - Multi-agent Embodied AI: Advances and Future Directions [46.23631919950584]
Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era.<n>This paper reviews the current state of research, analyzes key contributions, and identifies challenges and future directions.
arXiv Detail & Related papers (2025-05-08T10:13:53Z) - AI Enhanced Ontology Driven NLP for Intelligent Cloud Resource Query Processing Using Knowledge Graphs [0.0]
This paper proposes an advanced Natural Language Processing (NLP) enhanced by ontology-based semantics to enable intuitive, human-readable queries.
The proposed framework enables dynamic intent extraction and relevance ranking using Latent Semantic Indexing (LSI) and AI models.
arXiv Detail & Related papers (2025-02-10T02:15:13Z) - Future of Information Retrieval Research in the Age of Generative AI [61.56371468069577]
In the fast-evolving field of information retrieval (IR), the integration of generative AI technologies such as large language models (LLMs) is transforming how users search for and interact with information.
Recognizing this paradigm shift, a visioning workshop was held in July 2024 to discuss the future of IR in the age of generative AI.
This report contains a summary of discussions as potentially important research topics and contains a list of recommendations for academics, industry practitioners, institutions, evaluation campaigns, and funding agencies.
arXiv Detail & Related papers (2024-12-03T00:01:48Z) - A Survey of Conversational Search [44.09402706387407]
We explore the recent advancements and potential future directions in conversational search.
We highlight the integration of large language models (LLMs) in enhancing these systems.
We provide insights into real-world applications and robust evaluations of current conversational search systems.
arXiv Detail & Related papers (2024-10-21T01:54:46Z) - Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective [111.58315434849047]
robustness of neural information retrieval models (IR) models has garnered significant attention.
We view the robustness of IR to be a multifaceted concept, emphasizing its necessity against adversarial attacks, out-of-distribution (OOD) scenarios and performance variance.
We provide an in-depth discussion of existing methods, datasets, and evaluation metrics, shedding light on challenges and future directions in the era of large language models.
arXiv Detail & Related papers (2024-07-09T16:07:01Z) - Self-Retrieval: End-to-End Information Retrieval with One Large Language Model [97.71181484082663]
We introduce Self-Retrieval, a novel end-to-end LLM-driven information retrieval architecture.
Self-Retrieval internalizes the retrieval corpus through self-supervised learning, transforms the retrieval process into sequential passage generation, and performs relevance assessment for reranking.
arXiv Detail & Related papers (2024-02-23T18:45:35Z) - Large Language Models for Information Retrieval: A Survey [58.30439850203101]
Information retrieval has evolved from term-based methods to its integration with advanced neural models.
Recent research has sought to leverage large language models (LLMs) to improve IR systems.
We delve into the confluence of LLMs and IR systems, including crucial aspects such as query rewriters, retrievers, rerankers, and readers.
arXiv Detail & Related papers (2023-08-14T12:47:22Z) - Synergistic Interplay between Search and Large Language Models for
Information Retrieval [141.18083677333848]
InteR allows RMs to expand knowledge in queries using LLM-generated knowledge collections.
InteR achieves overall superior zero-shot retrieval performance compared to state-of-the-art methods.
arXiv Detail & Related papers (2023-05-12T11:58:15Z) - Conceptual Modeling and Artificial Intelligence: A Systematic Mapping
Study [0.5156484100374059]
In conceptual modeling (CM), humans apply abstraction to represent excerpts of reality for means of understanding and communication, and processing by machines.
Recently, a trend toward intertwining CM and AI emerged.
This systematic mapping study shows how this interdisciplinary research field is structured, which mutual benefits are gained by the intertwining, and future research directions.
arXiv Detail & Related papers (2023-03-12T21:23:46Z) - Retrieval-Enhanced Machine Learning [110.5237983180089]
We describe a generic retrieval-enhanced machine learning framework, which includes a number of existing models as special cases.
REML challenges information retrieval conventions, presenting opportunities for novel advances in core areas, including optimization.
REML research agenda lays a foundation for a new style of information access research and paves a path towards advancing machine learning and artificial intelligence.
arXiv Detail & Related papers (2022-05-02T21:42:45Z) - Neural Approaches to Conversational Information Retrieval [94.77863916314979]
A conversational information retrieval (CIR) system is an information retrieval (IR) system with a conversational interface.
Recent progress in deep learning has brought tremendous improvements in natural language processing (NLP) and conversational AI.
This book surveys recent advances in CIR, focusing on neural approaches that have been developed in the last few years.
arXiv Detail & Related papers (2022-01-13T19:04:59Z) - Neural Methods for Effective, Efficient, and Exposure-Aware Information
Retrieval [7.3371176873092585]
We present novel neural architectures and methods motivated by the specific needs and challenges of information retrieval.
In many real-life IR tasks, the retrieval involves extremely large collections--such as the document index of a commercial Web search engine--containing billions of documents.
arXiv Detail & Related papers (2020-12-21T21:20:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.