[PDF][PDF] Constraint modelling with LLMs using in-context learning

K Michailidis, D Tsouros, T Guns - 30th International conference …, 2024 - lirias.kuleuven.be
Constraint Programming (CP) allows for the modelling and solving of a wide range of
combinatorial problems. However, modelling such problems using constraints over decision …

The role of foundation models in neuro-symbolic learning and reasoning

D Cunnington, M Law, J Lobo, A Russo - International Conference on …, 2024 - Springer
Abstract Neuro-Symbolic AI (NeSy) holds promise to ensure the safe deployment of AI
systems, as interpretable symbolic techniques provide formal behaviour guarantees. The …

Deisam: Segment anything with deictic prompting

H Shindo, M Brack, G Sudhakaran, DS Dhami… - arXiv preprint arXiv …, 2024 - arxiv.org
Large-scale, pre-trained neural networks have demonstrated strong capabilities in various
tasks, including zero-shot image segmentation. To identify concrete objects in complex …

Extending Answer Set Programming with Rational Numbers

F Pacenza, J Zangari - arXiv preprint arXiv:2312.04249, 2023 - arxiv.org
Answer Set Programming (ASP) is a widely used declarative programming paradigm that
has shown great potential in solving complex computational problems. However, the …

BlendRL: A Framework for Merging Symbolic and Neural Policy Learning

H Shindo, Q Delfosse, DS Dhami, K Kersting - arXiv preprint arXiv …, 2024 - arxiv.org
Humans can leverage both symbolic reasoning and intuitive reactions. In contrast,
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 …

Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets

T Eiter, J Hadl, N Higuera, J Oetsch - arXiv preprint arXiv:2410.09428, 2024 - arxiv.org
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 …

Towards Automatic Composition of ASP Programs from Natural Language Specifications

M Borroto, I Kareem, F Ricca - arXiv preprint arXiv:2403.04541, 2024 - arxiv.org
This paper moves the first step towards automating the composition of Answer Set
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 …

Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?

N Tyagi, M Parmar, M Kulkarni, A Rrv, N Patel… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …