Jakub Podolak

3 papers · 2024–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 👥 Mega-Team · Squad

Venues

EMNLP (2) ICML (1)

Top co-authors

Daniel Timbrell (1) Athanasios Theocharis (1) Julia Bazinska (1) Piotr Sankowski (1) Katarzyna Bakowicz (1) Samuel Trautwein (1) Manuel Knott (1) Mateo Rojas-Carulla (1) Matthew Fiedler (1) Rajeev Verma (1)

Research topics

Artificial Intelligence (3) Machine Learning (3) Core AI (3) Learning Types (2) Natural Language Processing (1) Application Areas (1) Generation (1) Optimization & Theory (1) Resources & Methods (1)

Keywords

question answering (1) chain-of-thought reasoning (1) text generation (1) content moderation (1) confidence calibration (1) uncertainty estimation (1) a/b testing (1) user engagement (1) hate speech detection (1) counterspeech generation (1) hate speech (1) large language model (1) adaptive defense (1) system prompt (1) semantic entropy (1) verbal confidence (1) prompt attack (1) reasoning budget (1) usability (1) crowd-sourced (1)

Papers

Gandalf the Red: Adaptive Security for LLMs ICML 2025 Read Your Own Mind: Reasoning Helps Surface Self-Confidence Signals in LLMs EMNLP 2025 LLM generated responses to mitigate the impact of hate speech EMNLP 2024