Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
BayesPrompt: human readable prompts that make sense
Franky Kevin Nando Tezoh, Ali Hussaini Umar, Alessandro Laio +2
Reconstructing prompts that can elicit a desired answer or behaviour in an LLM is an open and important research topic. Optimisation methods which aim at minimising the perplexity…
cs.CL2026
Differential syntactic and semantic encoding in LLMs
Santiago Acevedo, Alessandro Laio, Marco Baroni
We study how syntactic and semantic information is encoded in inner layer representations of Large Language Models (LLMs), focusing on the very large DeepSeek-V3. We find that, by…
cs.CL2025
A quantitative analysis of semantic information in deep representations of text and images
Santiago Acevedo, Andrea Mascaretti, Riccardo Rende +3
It was recently observed that the representations of different models that process identical or semantically related inputs tend to align. We analyze this phenomenon using the Info…