In this paper, we investigate various aspects of embedding models that could influence the recoverability of text using Vec2Text.
Our ReSLLM method exploits LLMs to drive the selection of resources in federated search in a zero-shot setting.
This paper considers Pseudo-Relevance Feedback (PRF) methods for dense retrievers in a resource constrained environment such as that of cheap cloud instances or embedded systems (e. g., smartphones and smartwatches), where memory and CPU are limited and GPUs are not present.
In this context, we show that there is no need for further pre-training if a domain-specific BERT backbone is used within the active learning pipeline.
Systematic reviews are crucial for evidence-based medicine as they comprehensively analyse published research findings on specific questions.
We describe team ielab from CSIRO and The University of Queensland's approach to the 2023 TREC Clinical Trials Track.
In the field of information retrieval, Query Likelihood Models (QLMs) rank documents based on the probability of generating the query given the content of a document.
Our approach reduces the number of LLM inferences and the amount of prompt token consumption during the ranking procedure, significantly improving the efficiency of LLM-based zero-shot ranking.
We find that ChatGPT provides correct or partially correct answers in about half of the cases (50. 6% of the times), but its suggested references only exist 14% of the times.
Our best approach is not only viable based on the information available at the time of screening, but also has similar effectiveness to the final title.
To improve diagnostic accuracy, we propose a CXR report generator that integrates aspects of the radiologist workflow and is trained with our proposed reward for reinforcement learning.
Aside from measuring the effectiveness of ChatGPT in this context, we show that the knowledge passed in the prompt can overturn the knowledge encoded in the model and this is, in our experiments, to the detriment of answer correctness.
The ability of ChatGPT to follow complex instructions and generate queries with high precision makes it a valuable tool for researchers conducting systematic reviews, particularly for rapid reviews where time is a constraint and often trading-off higher precision for lower recall is acceptable.
On the basis of these needs we release an information retrieval test collection comprising real questions, a large collection of scientific documents split in passages, and ground truth relevance assessments indicating which passages are relevant to each question.
An empirical analysis compares how effective neural methods compare to traditional methods for this task.
However, identifying the correct MeSH terms to include in a query is difficult: information experts are often unfamiliar with the MeSH database and unsure about the appropriateness of MeSH terms for a query.
Pseudo-Relevance Feedback (PRF) assumes that the top results retrieved by a first-stage ranker are relevant to the original query and uses them to improve the query representation for a second round of retrieval.
However, we show pseudo seed studies are not representative of real seed studies used by information specialists.
Our experimental investigation demonstrates that the Convolutional vision Transformer (CvT) ImageNet-21K and the Distilled Generative Pre-trained Transformer 2 (DistilGPT2) checkpoints are best for warm starting the encoder and decoder, respectively.
Finding concepts in large clinical ontologies can be challenging when queries use different vocabularies.
Text-based PRF results show that the use of PRF had a mixed effect on deep rerankers across different datasets.