6 papers · 1 filter
iPOE: Interpretable Prompt Optimization via Explanations
Jiahui Li, Yarik Menchaca Resendiz, Sean Papay +1
Prompt optimization has often been framed as a discrete search problem to find high-performing and robust instructions for a large language model (LLM). However, the search result…
Are Humans as Brittle as Large Language Models?
Jiahui Li, Sean Papay, Roman Klinger
The output of large language models (LLMs) is unstable, due both to non-determinism of the decoding process as well as to prompt brittleness. While the intrinsic non-determinism of…
Efficient Language Modeling for Low-Resource Settings with Hybrid RNN-Transformer Architectures
Gabriel Lindenmaier, Sean Papay, Sebastian Padó
Transformer-based language models have recently been at the forefront of active research in text generation. However, these models' advances come at the price of prohibitive traini…
Which Demographics do LLMs Default to During Annotation?
Johannes Schäfer, Aidan Combs, Christopher Bagdon +9
Demographics and cultural background of annotators influence the labels they assign in text annotation -- for instance, an elderly woman might find it offensive to read a message a…
Actor Identification in Discourse: A Challenge for LLMs?
Ana Barić, Sean Papay, Sebastian Padó
The identification of political actors who put forward claims in public debate is a crucial step in the construction of discourse networks, which are helpful to analyze societal de…
Dissecting Span Identification Tasks with Performance Prediction
Sean Papay, Roman Klinger, Sebastian Padó
Span identification (in short, span ID) tasks such as chunking, NER, or code-switching detection, ask models to identify and classify relevant spans in a text. Despite being a stap…