15 citations · 25 across the 13 of their papers we have counts for
13 papers
Entropy-Aligned Decoding of LMs for Better Writing and Reasoning
Kareem Ahmed, Sameer Singh
Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generati…
Controllable Generation via Locally Constrained Resampling
Kareem Ahmed, Kai-Wei Chang, Guy Van den Broeck
Autoregressive models have demonstrated an unprecedented ability at modeling the intricacies of natural language. However, they continue to struggle with generating complex outputs…
Where is the signal in tokenization space?
Renato Lui Geh, Honghua Zhang, Kareem Ahmed +2
Large Language Models (LLMs) are typically shipped with tokenizers that deterministically encode text into so-called canonical token sequences, to which the LLMs assign probability…
Scaling Tractable Probabilistic Circuits: A Systems Perspective
Anji Liu, Kareem Ahmed, Guy Van den Broeck
Probabilistic Circuits (PCs) are a general framework for tractable deep generative models, which support exact and efficient probabilistic inference on their learned distributions.…
Semantic Loss Functions for Neuro-Symbolic Structured Prediction
Kareem Ahmed, Stefano Teso, Paolo Morettin +8
Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the in…
A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
Kareem Ahmed, Kai-Wei Chang, Guy Van den Broeck
Neuro-symbolic AI bridges the gap between purely symbolic and neural approaches to learning. This often requires maximizing the likelihood of a symbolic constraint w.r.t the neural…
A Unified Approach to Count-Based Weakly-Supervised Learning
Vinay Shukla, Zhe Zeng, Kareem Ahmed +1
High-quality labels are often very scarce, whereas unlabeled data with inferred weak labels occurs more naturally. In many cases, these weak labels dictate the frequency of each re…
Probabilistically Rewired Message-Passing Neural Networks
Chendi Qian, Andrei Manolache, Kareem Ahmed +4
Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input. However, they operate on a fixed input graph structure, ignoring pote…
Semantic Strengthening of Neuro-Symbolic Learning
Kareem Ahmed, Kai-Wei Chang, Guy Van den Broeck
Numerous neuro-symbolic approaches have recently been proposed typically with the goal of adding symbolic knowledge to the output layer of a neural network. Ideally, such losses ma…
SIMPLE: A Gradient Estimator for -Subset Sampling
Kareem Ahmed, Zhe Zeng, Mathias Niepert +1
-subset sampling is ubiquitous in machine learning, enabling regularization and interpretability through sparsity. The challenge lies in rendering -subset sampling amenable t…
Semantic Probabilistic Layers for Neuro-Symbolic Learning
Kareem Ahmed, Stefano Teso, Kai-Wei Chang +2
We design a predictive layer for structured-output prediction (SOP) that can be plugged into any neural network guaranteeing its predictions are consistent with a set of predefined…
Neuro-Symbolic Entropy Regularization
Kareem Ahmed, Eric Wang, Kai-Wei Chang +1
In structured prediction, the goal is to jointly predict many output variables that together encode a structured object -- a path in a graph, an entity-relation triple, or an order…
Leveraging Unlabeled Data for Entity-Relation Extraction through Probabilistic Constraint Satisfaction
Kareem Ahmed, Eric Wang, Guy Van den Broeck +1
We study the problem of entity-relation extraction in the presence of symbolic domain knowledge. Such knowledge takes the form of an ontology defining relations and their permissib…