Search Results for author:
Found 17 papers, 10 papers with code
Noise to the Rescue: Escaping Local Minima in Neurosymbolic Local Search
We show that applying BP to Godel logic, which represents conjunction and disjunction as min and max, is equivalent to a local search algorithm for SAT solving, enabling the optimisation of discrete Boolean formulas without sacrificing differentiability.
Self-Training Large Language Models for Tool-Use Without Demonstrations
Large language models (LLMs) remain prone to factual inaccuracies and computational errors, including hallucinations and mistakes in mathematical reasoning.
Mixtures of In-Context Learners
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 memory.
A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
The advent of powerful neural classifiers has increased interest in problems that require both learning and reasoning.
Are We Done with MMLU?
For example, we find that 57% of the analysed questions in the Virology subset contain errors.
ULLER: A Unified Language for Learning and Reasoning
The field of neuro-symbolic artificial intelligence (NeSy), which combines learning and reasoning, has recently experienced significant growth.
On the Independence Assumption in Neurosymbolic Learning
Many such systems assume that the probabilities of the considered symbols are conditionally independent given the input to simplify learning and reasoning.
BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
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.
Optimisation in Neurosymbolic Learning Systems
How do we connect the symbolic and neural components to communicate this knowledge?
GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks
To this end, we introduce GRAPES, an adaptive sampling method that learns to identify the set of nodes crucial for training a GNN.
IntelliGraphs: Datasets for Benchmarking Knowledge Graph Generation
However, Knowledge Graphs are not just sets of links but also have semantics underlying their structure.
Prompting as Probing: Using Language Models for Knowledge Base Construction
ProP implements a multi-step approach that combines a variety of prompting techniques to achieve this.
Refining neural network predictions using background knowledge
Using a new algorithm called Iterative Local Refinement (ILR), we combine refinement functions to find refined predictions for logical formulas of any complexity.
Storchastic: A Framework for General Stochastic Automatic Differentiation
Stochastic AD extends AD to stochastic computation graphs with sampling steps, which arise when modelers handle the intractable expectations common in Reinforcement Learning and Variational Inference.
Analyzing Differentiable Fuzzy Implications
In this paper, we investigate how implications from the fuzzy logic literature behave in a differentiable setting.
Analyzing Differentiable Fuzzy Logic Operators
Finally, we empirically show that it is possible to use Differentiable Fuzzy Logics for semi-supervised learning, and compare how different operators behave in practice.
Semi-Supervised Learning using Differentiable Reasoning
We introduce Differentiable Reasoning (DR), a novel semi-supervised learning technique which uses relational background knowledge to benefit from unlabeled data.
