4 papers
Late Transformer Layers Recode Syntax Canonically: Evidence from Greek Scrambling and Cross-Layer Generalisation
Christos Nikolaos Zacharopoulos, Revekka Kyriakoglou, Chara Tsoukala +1
Probing studies have established that syntactic information is decodable in early and middle transformer layers, but what happens to that information in later layers remains poorly…
In Machina N400: Pinpointing Where a Causal Language Model Detects Semantic Violations
Christos-Nikolaos Zacharopoulos, Revekka Kyriakoglou
How and where does a transformer notice that a sentence has gone semantically off the rails? To explore this question, we evaluated the causal language model (phi-2) using a carefu…
Decoding Emergent Big Five Traits in Large Language Models: Temperature-Dependent Expression and Architectural Clustering
Christos-Nikolaos Zacharopoulos, Revekka Kyriakoglou
As Large Language Models (LLMs) become integral to human-centered applications, understanding their personality-like behaviors is increasingly important for responsible development…
Assessing the influence of attractor-verb distance on grammatical agreement in humans and language models
Christos-Nikolaos Zacharopoulos, Théo Desbordes, Mathias Sablé-Meyer
Subject-verb agreement in the presence of an attractor noun located between the main noun and the verb elicits complex behavior: judgments of grammaticality are modulated by the gr…