1 citations · 1 across the 6 of their papers we have counts for
6 papers
Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representations
Marco Baroni, Emily Cheng, Iria de-Dios-Flores +1
We explore intrinsic dimension (ID) of LLM representations as a marker of linguistic complexity. Specifically, we test whether ID differences across model layers reflect well-known…
Evil twins are not that evil: Qualitative insights into machine-generated prompts
Nathanaël Carraz Rakotonirina, Corentin Kervadec, Francesca Franzon +1
It has been widely observed that language models (LMs) respond in predictable ways to algorithmically generated prompts that are seemingly unintelligible. This is both a sign that…
Emergence of a High-Dimensional Abstraction Phase in Language Transformers
Emily Cheng, Diego Doimo, Corentin Kervadec +4
A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate…
MemoryPrompt: A Light Wrapper to Improve Context Tracking in Pre-trained Language Models
Nathanaël Carraz Rakotonirina, Marco Baroni
Transformer-based language models (LMs) track contextual information through large, hard-coded input windows. We introduce MemoryPrompt, a leaner approach in which the LM is comple…
Bridging Information-Theoretic and Geometric Compression in Language Models
Emily Cheng, Corentin Kervadec, Marco Baroni
For a language model (LM) to faithfully model human language, it must compress vast, potentially infinite information into relatively few dimensions. We propose analyzing compressi…
Unnatural language processing: How do language models handle machine-generated prompts?
Corentin Kervadec, Francesca Franzon, Marco Baroni
Language model prompt optimization research has shown that semantically and grammatically well-formed manually crafted prompts are routinely outperformed by automatically generated…