[PDF][PDF] Constraint modelling with LLMs using in-context learning
Constraint Programming (CP) allows for the modelling and solving of a wide range of
combinatorial problems. However, modelling such problems using constraints over decision …
combinatorial problems. However, modelling such problems using constraints over decision …
The role of foundation models in neuro-symbolic learning and reasoning
Abstract Neuro-Symbolic AI (NeSy) holds promise to ensure the safe deployment of AI
systems, as interpretable symbolic techniques provide formal behaviour guarantees. The …
systems, as interpretable symbolic techniques provide formal behaviour guarantees. The …
Deisam: Segment anything with deictic prompting
Large-scale, pre-trained neural networks have demonstrated strong capabilities in various
tasks, including zero-shot image segmentation. To identify concrete objects in complex …
tasks, including zero-shot image segmentation. To identify concrete objects in complex …
Extending Answer Set Programming with Rational Numbers
Answer Set Programming (ASP) is a widely used declarative programming paradigm that
has shown great potential in solving complex computational problems. However, the …
has shown great potential in solving complex computational problems. However, the …
BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
Humans can leverage both symbolic reasoning and intuitive reactions. In contrast,
reinforcement learning policies are typically encoded in either opaque systems like neural …
reinforcement learning policies are typically encoded in either opaque systems like neural …
TIC: Translate-Infer-Compile for accurate'text to plan'using LLMs and logical intermediate representations
S Agarwal, A Sreepathy - arXiv preprint arXiv:2402.06608, 2024 - arxiv.org
We study the problem of generating plans for given natural language planning task
requests. On one hand, LLMs excel at natural language processing but do not perform well …
requests. On one hand, LLMs excel at natural language processing but do not perform well …
Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets
Visual Question Answering (VQA) is the task of answering a question about an image and
requires processing multimodal input and reasoning to obtain the answer. Modular solutions …
requires processing multimodal input and reasoning to obtain the answer. Modular solutions …
Towards Automatic Composition of ASP Programs from Natural Language Specifications
This paper moves the first step towards automating the composition of Answer Set
Programming (ASP) specifications. In particular, the following contributions are provided:(i) …
Programming (ASP) specifications. In particular, the following contributions are provided:(i) …
A Pipeline of Neural-Symbolic Integration to Enhance Spatial Reasoning in Large Language Models
R Wang, K Sun, J Kuhn - arXiv preprint arXiv:2411.18564, 2024 - arxiv.org
Large Language Models (LLMs) have demonstrated impressive capabilities across various
tasks. However, LLMs often struggle with spatial reasoning which is one essential part of …
tasks. However, LLMs often struggle with spatial reasoning which is one essential part of …
Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?
Solving grid puzzles involves a significant amount of logical reasoning. Hence, it is a good
domain to evaluate the reasoning capability of a model which can then guide us to improve …
domain to evaluate the reasoning capability of a model which can then guide us to improve …