Coupling large language models with logic programming for robust and general reasoning from text
While large language models (LLMs), such as GPT-3, appear to be robust and general, their
reasoning ability is not at a level to compete with the best models trained for specific natural …
reasoning ability is not at a level to compete with the best models trained for specific natural …
When can transformers ground and compose: Insights from compositional generalization benchmarks
Humans can reason compositionally whilst grounding language utterances to the real world.
Recent benchmarks like ReaSCAN use navigation tasks grounded in a grid world to assess …
Recent benchmarks like ReaSCAN use navigation tasks grounded in a grid world to assess …
Imagine the unseen world: a benchmark for systematic generalization in visual world models
Systematic compositionality, or the ability to adapt to novel situations by creating a mental
model of the world using reusable pieces of knowledge, remains a significant challenge in …
model of the world using reusable pieces of knowledge, remains a significant challenge in …
Can LLM find the green circle? Investigation and Human-guided tool manipulation for compositional generalization
The meaning of complex phrases in natural language is composed of their individual
components. The task of compositional generalization evaluates a model's ability to …
components. The task of compositional generalization evaluates a model's ability to …
Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking
R Tamari, K Richardson, A Sar-Shalom… - arXiv preprint arXiv …, 2021 - arxiv.org
While neural language models often perform surprisingly well on natural language
understanding (NLU) tasks, their strengths and limitations remain poorly understood …
understanding (NLU) tasks, their strengths and limitations remain poorly understood …
A Survey on Compositional Learning of AI Models: Theoretical and Experimetnal Practices
S Sinha, T Premsri, P Kordjamshidi - arXiv preprint arXiv:2406.08787, 2024 - arxiv.org
Compositional learning, mastering the ability to combine basic concepts and construct more
intricate ones, is crucial for human cognition, especially in human language comprehension …
intricate ones, is crucial for human cognition, especially in human language comprehension …
Compositional Generalization in Neuro-Symbolic Visual Question Answering
A Dahlgren, S Dan - … Joint Conference on Artificial Intelligence 2023 …, 2023 - openreview.net
Compositional generalization is a key challenge in artificial intelligence. This paper
investigates compositional generalization capabilities in multimodal mathematical reasoning …
investigates compositional generalization capabilities in multimodal mathematical reasoning …
Look Further Ahead: Testing the Limits of GPT-4 in Path Planning
Large Language Models (LLMs) have shown impressive capabilities across a wide variety
of tasks. However, they still face challenges with long-horizon planning. To study this, we …
of tasks. However, they still face challenges with long-horizon planning. To study this, we …
Compositional generalization in grounded language learning via induced model sparsity
S Spilsbury, A Ilin - arXiv preprint arXiv:2207.02518, 2022 - arxiv.org
We provide a study of how induced model sparsity can help achieve compositional
generalization and better sample efficiency in grounded language learning problems. We …
generalization and better sample efficiency in grounded language learning problems. We …
Syntax-Guided Transformers: Elevating Compositional Generalization and Grounding in Multimodal Environments
D Kamali, P Kordjamshidi - arXiv preprint arXiv:2311.04364, 2023 - arxiv.org
Compositional generalization, the ability of intelligent models to extrapolate understanding
of components to novel compositions, is a fundamental yet challenging facet in AI research …
of components to novel compositions, is a fundamental yet challenging facet in AI research …