🧠 LLMs and Multi-Hop Queries: A Latent Reasoning Analysis
Impossible d'ajouter des articles
Échec de l’élimination de la liste d'envies.
Impossible de suivre le podcast
Impossible de ne plus suivre le podcast
🧠 LLMs and Multi-Hop Queries: A Latent Reasoning Analysis
-
Lu par :
-
De :
À propos de ce contenu audio
One study investigates whether a chess-playing neural network, Leela, learns look-ahead capabilities, finding evidence that it internally represents and uses future moves in its decision-making, employing mechanisms like activation patching and attention analysis to support this. Another paper explores the limitations of large language models (LLMs) in multi-hop reasoning, hypothesising a sequential "knowledge-extraction module" and using a technique called Patchscopes to locate these processes within the network, alongside back-patching experiments to further understand the model's reasoning pathway. Finally, the third source examines if LLMs share representations of grammatical concepts across diverse languages by training sparse autoencoders and using causal interventions, revealing that abstract grammatical concepts are often encoded in shared feature directions, suggesting a degree of language-independent understanding.
Vous êtes membre Amazon Prime ?
Bénéficiez automatiquement de 2 livres audio offerts.Bonne écoute !