Zobrazeno 1 - 10
of 1 005
pro vyhledávání: '"P. van Krieken"'
In-context learning (ICL) adapts LLMs by providing demonstrations without fine-tuning the model parameters; however, it does not differentiate between demonstrations and quadratically increases the complexity of Transformer LLMs, exhausting the memor
Externí odkaz:
http://arxiv.org/abs/2411.02830
Autor:
Bortolotti, Samuele, Marconato, Emanuele, Carraro, Tommaso, Morettin, Paolo, van Krieken, Emile, Vergari, Antonio, Teso, Stefano, Passerini, Andrea
The advent of powerful neural classifiers has increased interest in problems that require both learning and reasoning. These problems are critical for understanding important properties of models, such as trustworthiness, generalization, interpretabi
Externí odkaz:
http://arxiv.org/abs/2406.10368
Autor:
Gema, Aryo Pradipta, Leang, Joshua Ong Jun, Hong, Giwon, Devoto, Alessio, Mancino, Alberto Carlo Maria, Saxena, Rohit, He, Xuanli, Zhao, Yu, Du, Xiaotang, Madani, Mohammad Reza Ghasemi, Barale, Claire, McHardy, Robert, Harris, Joshua, Kaddour, Jean, van Krieken, Emile, Minervini, Pasquale
Maybe not. We identify and analyse errors in the popular Massive Multitask Language Understanding (MMLU) benchmark. Even though MMLU is widely adopted, our analysis demonstrates numerous ground truth errors that obscure the true capabilities of LLMs.
Externí odkaz:
http://arxiv.org/abs/2406.04127
The field of neuro-symbolic artificial intelligence (NeSy), which combines learning and reasoning, has recently experienced significant growth. There now are a wide variety of NeSy frameworks, each with its own specific language for expressing backgr
Externí odkaz:
http://arxiv.org/abs/2405.00532
State-of-the-art neurosymbolic learning systems use probabilistic reasoning to guide neural networks towards predictions that conform to logical constraints over symbols. Many such systems assume that the probabilities of the considered symbols are c
Externí odkaz:
http://arxiv.org/abs/2404.08458
Autor:
Marconato, Emanuele, Bortolotti, Samuele, van Krieken, Emile, Vergari, Antonio, Passerini, Andrea, Teso, Stefano
Neuro-Symbolic (NeSy) predictors that conform to symbolic knowledge - encoding, e.g., safety constraints - can be affected by Reasoning Shortcuts (RSs): They learn concepts consistent with the symbolic knowledge by exploiting unintended semantics. RS
Externí odkaz:
http://arxiv.org/abs/2402.12240
Autor:
van Krieken, Emile
Neurosymbolic AI aims to integrate deep learning with symbolic AI. This integration has many promises, such as decreasing the amount of data required to train a neural network, improving the explainability and interpretability of answers given by mod
Externí odkaz:
http://arxiv.org/abs/2401.10819
Autor:
Younesian, Taraneh, Daza, Daniel, van Krieken, Emile, Thanapalasingam, Thiviyan, Bloem, Peter
Graph neural networks (GNNs) learn to represent nodes by aggregating information from their neighbors. As GNNs increase in depth, their receptive field grows exponentially, leading to high memory costs. Several existing methods address this by sampli
Externí odkaz:
http://arxiv.org/abs/2310.03399
Knowledge Graph Embedding (KGE) models are used to learn continuous representations of entities and relations. A key task in the literature is predicting missing links between entities. However, Knowledge Graphs are not just sets of links but also ha
Externí odkaz:
http://arxiv.org/abs/2307.06698
Autor:
van Krieken, Emile, Thanapalasingam, Thiviyan, Tomczak, Jakub M., van Harmelen, Frank, Teije, Annette ten
We study the problem of combining neural networks with symbolic reasoning. Recently introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as DeepProbLog, perform exponential-time exact inference, limiting the scalability of PNL s
Externí odkaz:
http://arxiv.org/abs/2212.12393