134 citations · 242 across the 39 of their papers we have counts for
7 papers · 1 filter
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
Andy Han, Kristina Fujimoto, Avidan Shah +5
Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promi…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
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…
Towards Formalizing Spuriousness of Biased Datasets Using Partial Information Decomposition
Barproda Halder, Faisal Hamman, Pasan Dissanayake +3
Spuriousness arises when there is an association between two or more variables in a dataset that are not causally related. In this work, we propose an explainability framework to p…
Representational Alignment Supports Effective Machine Teaching
Ilia Sucholutsky, Katherine M. Collins, Maya Malaviya +11
A good teacher should not only be knowledgeable, but should also be able to communicate in a way that the student understands -- to share the student's representation of the world.…
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…
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…