Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
6 papers from Allen Institute for AI (AI2) on Reasoning & Chain-of-Thought
Confident conflicts in LLM distillation are mitigated by dynamically mixing student and teacher distributions based on student entropy, boosting reasoning and preserving general capabilities.
Discarding irrelevant reasoning tokens can make language models up to 3x faster at test time without sacrificing performance.
Operadic consistency reveals a powerful new way to diagnose reasoning failures in LLMs, achieving correlations with accuracy that exceed traditional confidence metrics.
By transforming LLM outputs into probabilistic programs, this approach slashes the computational cost of generating multiple code samples without sacrificing quality.
LLM agents can appear to reason well (high entropy) while completely ignoring the input, and mutual information is a far better metric for catching this failure.
Robot foundation models can achieve state-of-the-art performance by explicitly reasoning about spatial plans as editable trajectory traces, rather than directly mapping perception to control.