5 papers
Position: Reasoning is a Learnable Rule-Based Process
Rachel Lawrence, Jacqueline Maasch
Autonomous reasoning is among the most scientifically and economically motivating topics in AI today. Historically the purview of symbolic AI, recent advances have mainly emerged f…
Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task
Alicia Curth, Rachel Lawrence, Sushrut Karmalkar +1
We investigate whether transformers use their depth adaptively across tasks of increasing difficulty. Using a controlled multi-hop relational reasoning task based on family stories…
Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency
Victoria Lin, Xinnuo Xu, Rachel Lawrence +4
Despite their strong performance on reasoning benchmarks, large language models (LLMs) have proven brittle when presented with counterfactual questions, suggesting weaknesses in th…
RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation
Xinnuo Xu, Rachel Lawrence, Kshitij Dubey +7
Recent Large Language Models (LLMs) have reported high accuracy on reasoning benchmarks. However, it is still unclear whether the observed results arise from true reasoning or from…
A Fourier Space Perspective on Diffusion Models
Fabian Falck, Teodora Pandeva, Kiarash Zahirnia +5
Diffusion models are state-of-the-art generative models on data modalities such as images, audio, proteins and materials. These modalities share the property of exponentially decay…