9 papers
Example-Guided Prompting for Document-Level Text Simplification
Marina Litvak, Ariel Perstin, Ilan Shtilman +1
Document-level text simplification requires large language models (LLMs) to rewrite complex documents while preserving meaning, readability, and discourse coherence. Although promp…
Topic-to-Timestamp Alignment by Constrained Evidence Selection
Zeynep Yılbırt, Marina Litvak, Michael Färber
Meeting archives are difficult to search when users remember what was discussed but not when. We study topic-to-timestamp alignment: given a natural-language topic and a timestampe…
Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation
Klaudia-Doris Thellmann, Bernhard Stadler, Michael Färber +1
Machine-translated benchmarks are widely used to assess the multilingual capabilities of large language models (LLMs), yet translation errors in these benchmarks remain underexplor…
Tracing Relational Knowledge Recall in Large Language Models
Nicholas PopoviÄ, Michael Färber
We study how large language models recall relational knowledge during text generation, with a focus on identifying latent representations suitable for relation classification via l…
Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models
Florian Kelber, Matthias Jobst, Yuni Susanti +1
Scientific knowledge discovery increasingly relies on large language models, yet many existing scholarly assistants depend on proprietary systems with tens or hundreds of billions…
Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference
Cornelius Kummer, Lena Jurkschat, Michael Färber +1
With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retri…