Zobrazeno 1 - 10
of 1 701
pro vyhledávání: '"Zuccon A"'
2D Matryoshka Training is an advanced embedding representation training approach designed to train an encoder model simultaneously across various layer-dimension setups. This method has demonstrated higher effectiveness in Semantic Text Similarity (S
Externí odkaz:
http://arxiv.org/abs/2411.17299
Effective approaches that can scale embedding model depth (i.e. layers) and embedding size allow for the creation of models that are highly scalable across different computational resources and task requirements. While the recently proposed 2D Matryo
Externí odkaz:
http://arxiv.org/abs/2410.13230
The emergence of Vec2Text -- a method for text embedding inversion -- has raised serious privacy concerns for dense retrieval systems which use text embeddings. This threat comes from the ability for an attacker with access to embeddings to reconstru
Externí odkaz:
http://arxiv.org/abs/2410.06628
Accurately estimating model performance poses a significant challenge, particularly in scenarios where the source and target domains follow different data distributions. Most existing performance prediction methods heavily rely on the source data in
Externí odkaz:
http://arxiv.org/abs/2408.02209
Autor:
Khramtsova, Ekaterina, Leelanupab, Teerapong, Zhuang, Shengyao, Baktashmotlagh, Mahsa, Zuccon, Guido
In this demo we present a web-based application for selecting an effective pre-trained dense retriever to use on a private collection. Our system, DenseQuest, provides unsupervised selection and ranking capabilities to predict the best dense retrieve
Externí odkaz:
http://arxiv.org/abs/2407.06685
The goal of screening prioritisation in systematic reviews is to identify relevant documents with high recall and rank them in early positions for review. This saves reviewing effort if paired with a stopping criterion, and speeds up review completio
Externí odkaz:
http://arxiv.org/abs/2407.00635
We provide a systematic understanding of the impact of specific components and wordings used in prompts on the effectiveness of rankers based on zero-shot Large Language Models (LLMs). Several zero-shot ranking methods based on LLMs have recently bee
Externí odkaz:
http://arxiv.org/abs/2406.14117
Autor:
Schlatt, Ferdinand, Fröbe, Maik, Scells, Harrisen, Zhuang, Shengyao, Koopman, Bevan, Zuccon, Guido, Stein, Benno, Potthast, Martin, Hagen, Matthias
Cross-encoders distilled from large language models (LLMs) are often more effective re-rankers than cross-encoders fine-tuned on manually labeled data. However, the distilled models usually do not reach their teacher LLM's effectiveness. To investiga
Externí odkaz:
http://arxiv.org/abs/2405.07920
Utilizing large language models (LLMs) for zero-shot document ranking is done in one of two ways: (1) prompt-based re-ranking methods, which require no further training but are only feasible for re-ranking a handful of candidate documents due to comp
Externí odkaz:
http://arxiv.org/abs/2404.18424
Autor:
Schlatt, Ferdinand, Fröbe, Maik, Scells, Harrisen, Zhuang, Shengyao, Koopman, Bevan, Zuccon, Guido, Stein, Benno, Potthast, Martin, Hagen, Matthias
Existing cross-encoder re-rankers can be categorized as pointwise, pairwise, or listwise models. Pair- and listwise models allow passage interactions, which usually makes them more effective than pointwise models but also less efficient and less robu
Externí odkaz:
http://arxiv.org/abs/2404.06912