4 papers · 1 filter
Analyzing LLM Instruction Optimization for Tabular Fact Verification
Xiaotang Du, Giwon Hong, Wai-Chung Kwan +4
Instruction optimization provides a lightweight, model-agnostic approach to enhancing the reasoning performance of large language models (LLMs). This paper presents the first syste…
Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing
Dennis Ulmer, Alexandra Lorson, Ivan Titov +1
Human users increasingly communicate with large language models (LLMs), but LLMs suffer from frequent overconfidence in their output, even when its accuracy is questionable, which…
Disentangling Textual and Acoustic Features of Neural Speech Representations
Hosein Mohebbi, Grzegorz ChrupaÅa, Willem Zuidema +2
Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic co…
Unlearning Traces the Influential Training Data of Language Models
Masaru Isonuma, Ivan Titov
Identifying the training datasets that influence a language model's outputs is essential for minimizing the generation of harmful content and enhancing its performance. Ideally, we…