Tag: cs.IR

Shotit: compute-efficient image-to-video search engine for the cloud

Leslie Wong Edit "Shotit: compute-efficient image-to-video search engine for the cloud"
arXiv:2404.12169v1 Announce Type: new Abstract: With the rapid growth of information technology, users are exposed to a massive amount of data online, including image, music, and video. This has led to strong needs to provide effective corresponsive search services such as image, music, and video search services. Most of them are operated based on keywords, namely using keywords to find related image, music, and video. Additionally, there are image-to-image search services that enable users to find similar images using one input image. Given that videos are essentially composed of image frames, then similar videos can be searched by one input image or screenshot. We want to target this scenario and provide an efficient method and implementation in this paper. We present Shotit, a cloud-native image-to-video search engine that tailors this search scenario in a compute-efficient approach. One main limitation faced in this scenario is the scale of its dataset. A typical image-to-image search engine only handles one-to-one relationships, colloquially, one image corresponds to another single image. But image-to-video proliferates. Take a 24-min length video as an example, it will generate roughly 20,000 image frames. As the number of videos grows, the scale of the dataset explodes exponentially. In this case, a compute-efficient approach ought to be considered, and the system design should cater to the cloud-native trend. Choosing an emerging technology - vector database as its backbone, Shotit fits these two metrics performantly. Experiments for two different datasets, a 50 thousand-scale Blender Open Movie dataset, and a 50 million-scale proprietary TV genre dataset at a 4 Core 32GB RAM Intel Xeon Gold 6271C cloud machine with object storage reveal the effectiveness of Shotit. A demo regarding the Blender Open Movie dataset is illustrated within this paper.

GOLF: Goal-Oriented Long-term liFe tasks supported by human-AI collaboration

Ben Wang Edit "GOLF: Goal-Oriented Long-term liFe tasks supported by human-AI collaboration"
arXiv:2403.17089v1 Announce Type: new Abstract: The advent of ChatGPT and similar large language models (LLMs) has revolutionized the human-AI interaction and information-seeking process. Leveraging LLMs as an alternative to search engines, users can now access summarized information tailored to their queries, significantly reducing the cognitive load associated with navigating vast information resources. This shift underscores the potential of LLMs in redefining information access paradigms. Drawing on the foundation of task-focused information retrieval and LLMs' task planning ability, this research extends the scope of LLM capabilities beyond routine task automation to support users in navigating long-term and significant life tasks. It introduces the GOLF framework (Goal-Oriented Long-term liFe tasks), which focuses on enhancing LLMs' ability to assist in significant life decisions through goal orientation and long-term planning. The methodology encompasses a comprehensive simulation study to test the framework's efficacy, followed by model and human evaluations to develop a dataset benchmark for long-term life tasks, and experiments across different models and settings. By shifting the focus from short-term tasks to the broader spectrum of long-term life goals, this research underscores the transformative potential of LLMs in enhancing human decision-making processes and task management, marking a significant step forward in the evolution of human-AI collaboration.

A Unified Optimal Transport Framework for Cross-Modal Retrieval with Noisy Labels

Haochen Han, Minnan Luo, Huan Liu, Fang Nan Edit "A Unified Optimal Transport Framework for Cross-Modal Retrieval with Noisy Labels"
arXiv:2403.13480v1 Announce Type: cross Abstract: Cross-modal retrieval (CMR) aims to establish interaction between different modalities, among which supervised CMR is emerging due to its flexibility in learning semantic category discrimination. Despite the remarkable performance of previous supervised CMR methods, much of their success can be attributed to the well-annotated data. However, even for unimodal data, precise annotation is expensive and time-consuming, and it becomes more challenging with the multimodal scenario. In practice, massive multimodal data are collected from the Internet with coarse annotation, which inevitably introduces noisy labels. Training with such misleading labels would bring two key challenges -- enforcing the multimodal samples to \emph{align incorrect semantics} and \emph{widen the heterogeneous gap}, resulting in poor retrieval performance. To tackle these challenges, this work proposes UOT-RCL, a Unified framework based on Optimal Transport (OT) for Robust Cross-modal Retrieval. First, we propose a semantic alignment based on partial OT to progressively correct the noisy labels, where a novel cross-modal consistent cost function is designed to blend different modalities and provide precise transport cost. Second, to narrow the discrepancy in multi-modal data, an OT-based relation alignment is proposed to infer the semantic-level cross-modal matching. Both of these two components leverage the inherent correlation among multi-modal data to facilitate effective cost function. The experiments on three widely-used cross-modal retrieval datasets demonstrate that our UOT-RCL surpasses the state-of-the-art approaches and significantly improves the robustness against noisy labels.

Navigating the Peril of Generated Alternative Facts: A ChatGPT-4 Fabricated Omega Variant Case as a Cautionary Tale in Medical Misinformation

Malik Sallam, Jan Egger, Rainer Roehrig, Behrus Puladi Edit "Navigating the Peril of Generated Alternative Facts: A ChatGPT-4 Fabricated Omega Variant Case as a Cautionary Tale in Medical Misinformation"
arXiv:2403.09674v1 Announce Type: new Abstract: In an era where artificial intelligence (AI) intertwines with medical research, the delineation of truth becomes increasingly complex. This study ostensibly examines a purported novel SARS-CoV-2 variant, dubbed the Omega variant, showcasing 31 unique mutations in the S gene region. However, the real undercurrent of this narrative is a demonstration of the ease with which AI, specifically ChatGPT-4, can fabricate convincing yet entirely fictional scientific data. The so-called Omega variant was identified in a fully vaccinated, previously infected 35-year-old male presenting with severe COVID-19 symptoms. Through a detailed, albeit artificial, genomic analysis and contact tracing, this study mirrors the rigorous methodology of genuine case reports, thereby setting the stage for a compelling but entirely constructed narrative. The entire case study was generated by ChatGPT-4, a large language model by OpenAI. The fabricated Omega variant features an ensemble of mutations, including N501Y and E484K, known for enhancing ACE2 receptor affinity, alongside L452R and P681H, ostensibly indicative of immune evasion. This variant's contrived interaction dynamics - severe symptoms in a vaccinated individual versus mild ones in unvaccinated contacts - were designed to mimic real-world complexities, including suggestions of antibody-dependent enhancement (ADE). While the Omega variant is a product of AI-generated fiction, the implications of this exercise are real and profound. The ease with which AI can generate believable but false scientific information, as illustrated in this case, raises significant concerns about the potential for misinformation in medicine. This study, therefore, serves as a cautionary tale, emphasizing the necessity for critical evaluation of sources, especially in an age where AI tools like ChatGPT are becoming increasingly sophisticated and widespread in their use.

Artificial Intelligence for Literature Reviews: Opportunities and Challenges

cs.HC updates on arXiv.org Edit "Artificial Intelligence for Literature Reviews: Opportunities and Challenges"
This manuscript presents a comprehensive review of the use of Artificial Intelligence (AI) in Systematic Literature Reviews (SLRs). A SLR is a rigorous and organised methodology that assesses and integrates previous research on a given topic. Numerous tools have been developed to assist and partially automate the SLR process. The increasing role of AI in this field shows great potential in providing more effective support for researchers, moving towards the semi-automatic creation of literature reviews. Our study focuses on how AI techniques are applied in the semi-automation of SLRs, specifically in the screening and extraction phases. We examine 21 leading SLR tools using a framework that combines 23 traditional features with 11 AI features. We also analyse 11 recent tools that leverage large language models for searching the literature and assisting academic writing. Finally, the paper discusses current trends in the field, outlines key research challenges, and suggests directions for future research.

From Data Creator to Data Reuser: Distance Matters

cs.HC updates on arXiv.org Edit "From Data Creator to Data Reuser: Distance Matters"
Sharing research data is complex, labor-intensive, expensive, and requires infrastructure investments by multiple stakeholders. Open science policies focus on data release rather than on data reuse, yet reuse is also difficult, expensive, and may never occur. Investments in data management could be made more wisely by considering who might reuse data, how, why, for what purposes, and when. Data creators cannot anticipate all possible reuses or reusers; our goal is to identify factors that may aid stakeholders in deciding how to invest in research data, how to identify potential reuses and reusers, and how to improve data exchange processes. Drawing upon empirical studies of data sharing and reuse, we develop the theoretical construct of distance between data creator and data reuser, identifying six distance dimensions that influence the ability to transfer knowledge effectively: domain, methods, collaboration, curation, purposes, and time and temporality. These dimensions are primarily social in character, with associated technical aspects that can decrease - or increase - distances between creators and reusers. We identify the order of expected influence on data reuse and ways in which the six dimensions are interdependent. Our theoretical framing of the distance between data creators and prospective reusers leads to recommendations to four categories of stakeholders on how to make data sharing and reuse more effective: data creators, data reusers, data archivists, and funding agencies.

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

cs.CL updates on arXiv.org Edit "C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models"
Despite the impressive capabilities of large language models (LLMs) across diverse applications, they still suffer from trustworthiness issues, such as hallucinations and misalignments. Retrieval-augmented language models (RAG) have been proposed to enhance the credibility of generations by grounding external knowledge, but the theoretical understandings of their generation risks remains unexplored. In this paper, we answer: 1) whether RAG can indeed lead to low generation risks, 2) how to provide provable guarantees on the generation risks of RAG and vanilla LLMs, and 3) what sufficient conditions enable RAG models to reduce generation risks. We propose C-RAG, the first framework to certify generation risks for RAG models. Specifically, we provide conformal risk analysis for RAG models and certify an upper confidence bound of generation risks, which we refer to as conformal generation risk. We also provide theoretical guarantees on conformal generation risks for general bounded risk functions under test distribution shifts. We prove that RAG achieves a lower conformal generation risk than that of a single LLM when the quality of the retrieval model and transformer is non-trivial. Our intensive empirical results demonstrate the soundness and tightness of our conformal generation risk guarantees across four widely-used NLP datasets on four state-of-the-art retrieval models.

The Power of Noise: Redefining Retrieval for RAG Systems

cs.CL updates on arXiv.org Edit "The Power of Noise: Redefining Retrieval for RAG Systems"
Retrieval-Augmented Generation (RAG) systems represent a significant advancement over traditional Large Language Models (LLMs). RAG systems enhance their generation ability by incorporating external data retrieved through an Information Retrieval (IR) phase, overcoming the limitations of standard LLMs, which are restricted to their pre-trained knowledge and limited context window. Most research in this area has predominantly concentrated on the generative aspect of LLMs within RAG systems. Our study fills this gap by thoroughly and critically analyzing the influence of IR components on RAG systems. This paper analyzes which characteristics a retriever should possess for an effective RAG's prompt formulation, focusing on the type of documents that should be retrieved. We evaluate various elements, such as the relevance of the documents to the prompt, their position, and the number included in the context. Our findings reveal, among other insights, that including irrelevant documents can unexpectedly enhance performance by more than 30% in accuracy, contradicting our initial assumption of diminished quality. These results underscore the need for developing specialized strategies to integrate retrieval with language generation models, thereby laying the groundwork for future research in this field.

Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models

cs.CL updates on arXiv.org Edit "Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models"
Dense retrieval (DR) converts queries and documents into dense embeddings and measures the similarity between queries and documents in vector space. One of the challenges in DR is the lack of domain-specific training data. While DR models can learn from large-scale public datasets like MS MARCO through transfer learning, evidence shows that not all DR models and domains can benefit from transfer learning equally. Recently, some researchers have resorted to large language models (LLMs) to improve the zero-shot and few-shot DR models. However, the hard prompts or human-written prompts utilized in these works cannot guarantee the good quality of generated weak queries. To tackle this, we propose soft prompt tuning for augmenting DR (SPTAR): For each task, we leverage soft prompt-tuning to optimize a task-specific soft prompt on limited ground truth data and then prompt the LLMs to tag unlabeled documents with weak queries, yielding enough weak document-query pairs to train task-specific dense retrievers. We design a filter to select high-quality example document-query pairs in the prompt to further improve the quality of weak tagged queries. To the best of our knowledge, there is no prior work utilizing soft prompt tuning to augment DR models. The experiments demonstrate that SPTAR outperforms the unsupervised baselines BM25 and the recently proposed LLMs-based augmentation method for DR.

DAPR: A Benchmark on Document-Aware Passage Retrieval

cs.CL updates on arXiv.org Edit "DAPR: A Benchmark on Document-Aware Passage Retrieval"
The work of neural retrieval so far focuses on ranking short texts and is challenged with long documents. There are many cases where the users want to find a relevant passage within a long document from a huge corpus, e.g. Wikipedia articles, research papers, etc. We propose and name this task \emph{Document-Aware Passage Retrieval} (DAPR). While analyzing the errors of the State-of-The-Art (SoTA) passage retrievers, we find the major errors (53.5\%) are due to missing document context. This drives us to build a benchmark for this task including multiple datasets from heterogeneous domains. In the experiments, we extend the SoTA passage retrievers with document context via (1) hybrid retrieval with BM25 and (2) contextualized passage representations, which inform the passage representation with document context. We find despite that hybrid retrieval performs the strongest on the mixture of the easy and the hard queries, it completely fails on the hard queries that require document-context understanding. On the other hand, contextualized passage representations (e.g. prepending document titles) achieve good improvement on these hard queries, but overall they also perform rather poorly. Our created benchmark enables future research on developing and comparing retrieval systems for the new task. The code and the data are available at https://https://github.com/UKPLab/arxiv2023-dapr.