2 citations · 2 across the 5 of their papers we have counts for
5 papers
Algebraic Decomposition Theory for Transformer Length Generalization
Andy Yang, Blerta Veseli, Corentin Barloy +5
Transformer-based language models are known to sometimes generalize to sequences longer than seen during training, but we lack a precise characterization of which tasks admit lengt…
Can LLMs subtract numbers?
Mayank Jobanputra, Nils Philipp Walter, Maitrey Mehta +7
We present a systematic study of subtraction in large language models (LLMs). While prior benchmarks emphasize addition and multiplication, subtraction has received comparatively l…
Positional Biases Shift as Inputs Approach Context Window Limits
Blerta Veseli, Julian Chibane, Mariya Toneva +1
Large Language Models (LLMs) often struggle to use information across long inputs effectively. Prior work has identified positional biases, such as the Lost in the Middle (LiM) eff…
Evaluating the Knowledge Base Completion Potential of GPT
Blerta Veseli, Simon Razniewski, Jan-Christoph Kalo +1
Structured knowledge bases (KBs) are an asset for search engines and other applications, but are inevitably incomplete. Language models (LMs) have been proposed for unsupervised kn…
Evaluating Language Models for Knowledge Base Completion
Blerta Veseli, Sneha Singhania, Simon Razniewski +1
Structured knowledge bases (KBs) are a foundation of many intelligent applications, yet are notoriously incomplete. Language models (LMs) have recently been proposed for unsupervis…