2 citations · 2 across the 5 of their papers we have counts for
4 papers · 1 filter
Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring
Mohammadali Mohammadkhani, Madhava Krishna, Yash Sarrof +1
Can reasoning models trick chain of thought (CoT) monitors and perform hidden computation without revealing it in their thinking traces? We show that the answer depends on the unde…
Barriers to Universal Reasoning With Transformers (And How to Overcome Them)
Oliver Kraus, Yash Sarrof, Yuekun Yao +2
Chain-of-Thought (CoT) has been shown to empirically improve Transformers' performance, and theoretically increase their expressivity to Turing completeness. However, whether Trans…
Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
Mayank Jobanputra, Yana Veitsman, Yash Sarrof +4
Transformers have theoretical limitations in modeling certain sequence-to-sequence tasks, yet it remains largely unclear if these limitations play a role in large-scale pretrained…
A Formal Framework for Understanding Length Generalization in Transformers
Xinting Huang, Andy Yang, Satwik Bhattamishra +5
A major challenge for transformers is generalizing to sequences longer than those observed during training. While previous works have empirically shown that transformers can either…