Zobrazeno 1 - 10
of 97
pro vyhledávání: '"Schnabel, Tobias"'
We explore the use of Large Language Model (LLM-based) chatbots to power recommender systems. We observe that the chatbots respond poorly when they encounter under-specified requests (e.g., they make incorrect assumptions, hedge with a long response,
Externí odkaz:
http://arxiv.org/abs/2406.01633
Autor:
Schnabel, Tobias, Neville, Jennifer
In many modern LLM applications, such as retrieval augmented generation, prompts have become programs themselves. In these settings, prompt programs are repeatedly called with different user queries or data instances. A big practical challenge is opt
Externí odkaz:
http://arxiv.org/abs/2404.02319
In recent years, neural models have been repeatedly touted to exhibit state-of-the-art performance in recommendation. Nevertheless, multiple recent studies have revealed that the reported state-of-the-art results of many neural recommendation models
Externí odkaz:
http://arxiv.org/abs/2305.01801
With information systems becoming larger scale, recommendation systems are a topic of growing interest in machine learning research and industry. Even though progress on improving model design has been rapid in research, we argue that many advances f
Externí odkaz:
http://arxiv.org/abs/2211.06365
Autor:
Schnabel, Tobias
Various studies in recent years have pointed out large issues in the offline evaluation of recommender systems, making it difficult to assess whether true progress has been made. However, there has been little research into what set of practices shou
Externí odkaz:
http://arxiv.org/abs/2211.01261
Autor:
Tagliabue, Jacopo, Bianchi, Federico, Schnabel, Tobias, Attanasio, Giuseppe, Greco, Ciro, Moreira, Gabriel de Souza P., Chia, Patrick John
Much of the complexity of Recommender Systems (RSs) comes from the fact that they are used as part of more complex applications and affect user experience through a varied range of user interfaces. However, research focused almost exclusively on the
Externí odkaz:
http://arxiv.org/abs/2207.05772
Most work in graph-based recommender systems considers a {\em static} setting where all information about test nodes (i.e., users and items) is available upfront at training time. However, this static setting makes little sense for many real-world ap
Externí odkaz:
http://arxiv.org/abs/2202.02427
Autor:
Ghiloufi, Mabrouka1 (AUTHOR) mabrouka.ghiloufi@fsb.ucar.tn, Schnabel, Tobias2 (AUTHOR) simon.mehling@hof-university.de, Mehling, Simon2 (AUTHOR), Kouass, Salah1 (AUTHOR) koissa2000@yahoo.fr
Publikováno v:
Materials (1996-1944). Sep2024, Vol. 17 Issue 18, p4671. 11p.
In the summarization domain, a key requirement for summaries is to be factually consistent with the input document. Previous work has found that natural language inference (NLI) models do not perform competitively when applied to inconsistency detect
Externí odkaz:
http://arxiv.org/abs/2111.09525
Publikováno v:
Association for Computational Linguistics (2021)
This work presents Keep it Simple (KiS), a new approach to unsupervised text simplification which learns to balance a reward across three properties: fluency, salience and simplicity. We train the model with a novel algorithm to optimize the reward (
Externí odkaz:
http://arxiv.org/abs/2107.03444