7.8k citations · 9.8k across the 15 of their papers we have counts for
5 papers · 1 filter
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
Caiqi Zhang, Xiaochen Zhu, Chengzu Li +3
Reliable confidence estimation is increasingly central to the trustworthy deployment of language models: a calibrated estimate of the probability that an output is correct decides…
How do LLMs Compute Verbal Confidence
Dharshan Kumaran, Arthur Conmy, Federico Barbero +3
Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from black-box models. However, how LLMs in…
Transformers need glasses! Information over-squashing in language tasks
Federico Barbero, Andrea Banino, Steven Kapturowski +5
We study how information propagates in decoder-only Transformers, which are the architectural backbone of most existing frontier large language models (LLMs). We rely on a theoreti…
Transformers generalize differently from information stored in context vs in weights
Stephanie C. Y. Chan, Ishita Dasgupta, Junkyung Kim +3
Transformer models can use two fundamentally different kinds of information: information stored in weights during training, and information provided ``in-context'' at inference tim…
Language models show human-like content effects on reasoning tasks
Ishita Dasgupta, Andrew K. Lampinen, Stephanie C. Y. Chan +5
Reasoning is a key ability for an intelligent system. Large language models (LMs) achieve above-chance performance on abstract reasoning tasks, but exhibit many imperfections. Howe…