23 citations · 95 across the 28 of their papers we have counts for
14 papers · 1 filter
SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search
Yifan Zhang, Giridhar Ganapavarapu, Srideepika Jayaraman +3
Large Language Models (LLMs) often falter at complex planning tasks that require exploration and self-correction, as their linear reasoning process struggles to recover from early…
Formally Specifying the High-Level Behavior of LLM-Based Agents
Maxwell Crouse, Ibrahim Abdelaziz, Ramon Astudillo +7
Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that ca…
An Ensemble Approach for Automated Theorem Proving Based on Efficient Name Invariant Graph Neural Representations
Achille Fokoue, Ibrahim Abdelaziz, Maxwell Crouse +5
Using reinforcement learning for automated theorem proving has recently received much attention. Current approaches use representations of logical statements that often rely on the…
Expressive Reasoning Graph Store: A Unified Framework for Managing RDF and Property Graph Databases
Sumit Neelam, Udit Sharma, Sumit Bhatia +5
Resource Description Framework (RDF) and Property Graph (PG) are the two most commonly used data models for representing, storing, and querying graph data. We present Expressive Re…
Learning to Guide a Saturation-Based Theorem Prover
Ibrahim Abdelaziz, Maxwell Crouse, Bassem Makni +8
Traditional automated theorem provers have relied on manually tuned heuristics to guide how they perform proof search. Recently, however, there has been a surge of interest in the…
An Experimental Study of Formula Embeddings for Automated Theorem Proving in First-Order Logic
Ibrahim Abdelaziz, Veronika Thost, Maxwell Crouse +1
Automated theorem proving in first-order logic is an active research area which is successfully supported by machine learning. While there have been various proposals for encoding…
Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling
Maxwell Crouse, Ibrahim Abdelaziz, Cristina Cornelio +4
Recent advances in the integration of deep learning with automated theorem proving have centered around the representation of logical formulae as inputs to deep learning systems. I…
Path-Based Contextualization of Knowledge Graphs for Textual Entailment
Kshitij Fadnis, Kartik Talamadupula, Pavan Kapanipathi +3
In this paper, we introduce the problem of knowledge graph contextualization -- that is, given a specific NLP task, the problem of extracting meaningful and relevant sub-graphs fro…
A Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving
Maxwell Crouse, Ibrahim Abdelaziz, Bassem Makni +7
Automated theorem provers have traditionally relied on manually tuned heuristics to guide how they perform proof search. Deep reinforcement learning has been proposed as a way to o…
High-Fidelity Vector Space Models of Structured Data
Maxwell Crouse, Achille Fokoue, Maria Chang +6
Machine learning systems regularly deal with structured data in real-world applications. Unfortunately, such data has been difficult to faithfully represent in a way that most mach…
Answering Science Exam Questions Using Query Rewriting with Background Knowledge
Ryan Musa, Xiaoyan Wang, Achille Fokoue +6
Open-domain question answering (QA) is an important problem in AI and NLP that is emerging as a bellwether for progress on the generalizability of AI methods and techniques. Much o…
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
Xiaoyan Wang, Pavan Kapanipathi, Ryan Musa +8
Natural Language Inference (NLI) is fundamental to many Natural Language Processing (NLP) applications including semantic search and question answering. The NLI problem has gained…
A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset
Michael Boratko, Harshit Padigela, Divyendra Mikkilineni +10
The recent work of Clark et al. introduces the AI2 Reasoning Challenge (ARC) and the associated ARC dataset that partitions open domain, complex science questions into an Easy Set…
An effective algorithm for hyperparameter optimization of neural networks
Gonzalo Diaz, Achille Fokoue, Giacomo Nannicini +1
A major challenge in designing neural network (NN) systems is to determine the best structure and parameters for the network given the data for the machine learning problem at hand…