3 papers
cs.CL2025
Understanding and Improving Information Preservation in Prompt Compression for LLMs
Weronika Łajewska, Momchil Hardalov, Laura Aina +3
Recent advancements in large language models (LLMs) have enabled their successful application to a broad range of tasks. However, in information-intensive tasks, the prompt length…
cs.CL2024
Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators
Matéo Mahaut, Laura Aina, Paula Czarnowska +3
Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM'…
cs.CL1998
Improving Tagging Performance by Using Voting Taggers
L. Marquez, L. Padro, H. Rodriguez
We present a bootstrapping method to develop an annotated corpus, which is specially useful for languages with few available resources. The method is being applied to develop a cor…