5 citations · 8 across the 6 of their papers we have counts for
7 papers
Uncovering Latent Reasoning Strategies in Language Models
Awni Altabaa, John Lafferty
A language model trained on reasoning tasks learns to solve problems via multiple distinct strategies, yet these strategies are implicit and entangled within the mo…
Unlocking Out-of-Distribution Generalization in Transformers via Recursive Latent Space Reasoning
Awni Altabaa, Siyu Chen, John Lafferty +1
Systematic, compositional generalization beyond the training distribution remains a core challenge in machine learning -- and a critical bottleneck for the emergent reasoning abili…
CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
Awni Altabaa, Omar Montasser, John Lafferty
Learning complex functions that involve multi-step reasoning poses a significant challenge for standard supervised learning from input-output examples. Chain-of-thought (CoT) super…
Disentangling and Integrating Relational and Sensory Information in Transformer Architectures
Awni Altabaa, John Lafferty
Relational reasoning is a central component of generally intelligent systems, enabling robust and data-efficient inductive generalization. Recent empirical evidence shows that many…
Approximation of relation functions and attention mechanisms
Awni Altabaa, John Lafferty
Inner products of neural network feature maps arise in a wide variety of machine learning frameworks as a method of modeling relations between inputs. This work studies the approxi…
Learning Hierarchical Relational Representations through Relational Convolutions
Awni Altabaa, John Lafferty
An evolving area of research in deep learning is the study of architectures and inductive biases that support the learning of relational feature representations. In this paper, we…
The Relational Bottleneck as an Inductive Bias for Efficient Abstraction
Taylor W. Webb, Steven M. Frankland, Awni Altabaa +9
A central challenge for cognitive science is to explain how abstract concepts are acquired from limited experience. This has often been framed in terms of a dichotomy between conne…