35 citations · 75 across the 19 of their papers we have counts for
8 papers · 1 filter
Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
Ryan Liu, Jiayi Geng, Addison J. Wu +3
Chain-of-thought (CoT) prompting has become a widely used strategy for improving large language and multimodal model performance. However, it is still an open question under which…
Large Language Models Assume People are More Rational than We Really are
Ryan Liu, Jiayi Geng, Joshua C. Peterson +2
In order for AI systems to communicate effectively with people, they must understand how we make decisions. However, people's decisions are not always rational, so the implicit int…
Learning with Language-Guided State Abstractions
Andi Peng, Ilia Sucholutsky, Belinda Z. Li +4
We describe a framework for using natural language to design state abstractions for imitation learning. Generalizable policy learning in high-dimensional observation spaces is faci…
Analyzing the Roles of Language and Vision in Learning from Limited Data
Allison Chen, Ilia Sucholutsky, Olga Russakovsky +1
Does language help make sense of the visual world? How important is it to actually see the world rather than having it described with words? These basic questions about the nature…
A Rational Analysis of the Speech-to-Song Illusion
Raja Marjieh, Pol van Rijn, Ilia Sucholutsky +3
The speech-to-song illusion is a robust psychological phenomenon whereby a spoken sentence sounds increasingly more musical as it is repeated. Despite decades of research, a comple…
Preference-Conditioned Language-Guided Abstraction
Andi Peng, Andreea Bobu, Belinda Z. Li +5
Learning from demonstrations is a common way for users to teach robots, but it is prone to spurious feature correlations. Recent work constructs state abstractions, i.e. visual rep…
Measuring Implicit Bias in Explicitly Unbiased Large Language Models
Xuechunzi Bai, Angelina Wang, Ilia Sucholutsky +1
Large language models (LLMs) can pass explicit social bias tests but still harbor implicit biases, similar to humans who endorse egalitarian beliefs yet exhibit subtle biases. Meas…
Concept Alignment
Sunayana Rane, Polyphony J. Bruna, Ilia Sucholutsky +2
Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that…