Tag
A new arXiv paper systematically tests five hypotheses for why large language models fail at tabular prediction, finding that dimensionality is the decisive factor: LLM accuracy degrades as input dimension grows, unlike classical baselines that stay flat or improve.
This paper investigates whether stochastic sampling (self-consistency) in LLMs can capture cross-question structure similar to diverse ensembles. Using a Marchenko–Pastur test, the authors find that within a single model, stochastic variation yields at most one significant dimension, while an ensemble of 24 models yields four, revealing a dimensionality gap that limits self-consistency as an ensemble substitute.
The article suggests that AI agents are often built with an implicit assumption of low-dimensional behavior, but the actual space they operate in is much higher-dimensional, leading to unexpected complexities.
This paper uses GPT-4.1 to annotate 9,000 support conversations and decompose customer satisfaction into component axes, validating the annotations against self-reported ratings and revealing lower satisfaction in full-census data compared to survey responses.
This paper investigates how much structure a task needs from a world model, showing that the objective's dimensionality determines how many predictive directions the model installs, with the common scalar reward objective being only the rank-one corner of value equivalence.
This research explores using hydrogels to increase the dimensionality of transistors, potentially enabling new flexible or bioelectronic devices.