3 papers
cs.CL2025
Read Your Own Mind: Reasoning Helps Surface Self-Confidence Signals in LLMs
Jakub Podolak, Rajeev Verma
We study the source of uncertainty in DeepSeek R1-32B by analyzing its self-reported verbal confidence on question answering (QA) tasks. In the default answer-then-confidence setti…
cs.LG2025
Gandalf the Red: Adaptive Security for LLMs
Niklas Pfister, Václav Volhejn, Manuel Knott +23
Current evaluations of defenses against prompt attacks in large language model (LLM) applications often overlook two critical factors: the dynamic nature of adversarial behavior an…
cs.IR2025
Beyond Reproducibility: Advancing Zero-shot LLM Reranking Efficiency with Setwise Insertion
Jakub Podolak, Leon Peric, Mina Janicijevic +1
This study presents a comprehensive reproducibility and extension analysis of the Setwise prompting methodology for zero-shot ranking with Large Language Models (LLMs), as proposed…