UKP Lab
@ukplab.bsky.social
The Ubiquitous Knowledge Processing Lab researches Natural Language Processing (#NLProc) with a strong emphasis on Large Language Models, Conversational AI & Question Answering | @cs-tudarmstadt.bsky.social · @TUDa.bsky.social
https://www.ukp.tu-darmstadt
https://www.ukp.tu-darmstadt
𝗧𝗵𝗲𝘀𝗶𝘀 𝗗𝗮𝘆 𝗮𝘁 𝘁𝗵𝗲 𝗨𝗞𝗣 𝗟𝗮𝗯 🎓
In the summer semester 2025, the UKP Lab accepted its largest cohort of thesis students to date, with more than 20 students. The group came together yesterday for a full-day workshop to present and discuss their final thesis work.
(1/🧵)
In the summer semester 2025, the UKP Lab accepted its largest cohort of thesis students to date, with more than 20 students. The group came together yesterday for a full-day workshop to present and discuss their final thesis work.
(1/🧵)
November 21, 2025 at 2:55 PM
𝗧𝗵𝗲𝘀𝗶𝘀 𝗗𝗮𝘆 𝗮𝘁 𝘁𝗵𝗲 𝗨𝗞𝗣 𝗟𝗮𝗯 🎓
In the summer semester 2025, the UKP Lab accepted its largest cohort of thesis students to date, with more than 20 students. The group came together yesterday for a full-day workshop to present and discuss their final thesis work.
(1/🧵)
In the summer semester 2025, the UKP Lab accepted its largest cohort of thesis students to date, with more than 20 students. The group came together yesterday for a full-day workshop to present and discuss their final thesis work.
(1/🧵)
🏅 𝗥𝗼𝘆𝗮𝗹 𝗦𝗼𝗰𝗶𝗲𝘁𝘆 𝗠𝗶𝗹𝗻𝗲𝗿 𝗔𝘄𝗮𝗿𝗱 𝟮𝟬𝟮𝟱 𝗳𝗼𝗿 𝗜𝗿𝘆𝗻𝗮 𝗚𝘂𝗿𝗲𝘃𝘆𝗰𝗵
Yesterday evening, Iryna Gurevych was honoured by @royalsociety.org with the 𝗠𝗶𝗹𝗻𝗲𝗿 𝗔𝘄𝗮𝗿𝗱 𝗮𝗻𝗱 𝗟𝗲𝗰𝘁𝘂𝗿𝗲 𝟮𝟬𝟮𝟱, one of the most prestigious distinctions in computer science.
Yesterday evening, Iryna Gurevych was honoured by @royalsociety.org with the 𝗠𝗶𝗹𝗻𝗲𝗿 𝗔𝘄𝗮𝗿𝗱 𝗮𝗻𝗱 𝗟𝗲𝗰𝘁𝘂𝗿𝗲 𝟮𝟬𝟮𝟱, one of the most prestigious distinctions in computer science.
November 18, 2025 at 2:11 PM
🏅 𝗥𝗼𝘆𝗮𝗹 𝗦𝗼𝗰𝗶𝗲𝘁𝘆 𝗠𝗶𝗹𝗻𝗲𝗿 𝗔𝘄𝗮𝗿𝗱 𝟮𝟬𝟮𝟱 𝗳𝗼𝗿 𝗜𝗿𝘆𝗻𝗮 𝗚𝘂𝗿𝗲𝘃𝘆𝗰𝗵
Yesterday evening, Iryna Gurevych was honoured by @royalsociety.org with the 𝗠𝗶𝗹𝗻𝗲𝗿 𝗔𝘄𝗮𝗿𝗱 𝗮𝗻𝗱 𝗟𝗲𝗰𝘁𝘂𝗿𝗲 𝟮𝟬𝟮𝟱, one of the most prestigious distinctions in computer science.
Yesterday evening, Iryna Gurevych was honoured by @royalsociety.org with the 𝗠𝗶𝗹𝗻𝗲𝗿 𝗔𝘄𝗮𝗿𝗱 𝗮𝗻𝗱 𝗟𝗲𝗰𝘁𝘂𝗿𝗲 𝟮𝟬𝟮𝟱, one of the most prestigious distinctions in computer science.
𝗧𝗵𝗲 𝘀𝗵𝗼𝘄 𝗴𝗼𝗲𝘀 𝗼𝗻 𝘁𝗼𝗱𝗮𝘆 𝗶𝗻 𝗟𝗼𝗻𝗱𝗼𝗻
After a productive first day, the UKP Lab continues its visit with a stop at The Alan Turing Institute.
🕙 Time: 10:00–12:00, 18 November
📍 Venue: Alan Turing Institute, British Library
After a productive first day, the UKP Lab continues its visit with a stop at The Alan Turing Institute.
🕙 Time: 10:00–12:00, 18 November
📍 Venue: Alan Turing Institute, British Library
November 18, 2025 at 12:15 PM
𝗧𝗵𝗲 𝘀𝗵𝗼𝘄 𝗴𝗼𝗲𝘀 𝗼𝗻 𝘁𝗼𝗱𝗮𝘆 𝗶𝗻 𝗟𝗼𝗻𝗱𝗼𝗻
After a productive first day, the UKP Lab continues its visit with a stop at The Alan Turing Institute.
🕙 Time: 10:00–12:00, 18 November
📍 Venue: Alan Turing Institute, British Library
After a productive first day, the UKP Lab continues its visit with a stop at The Alan Turing Institute.
🕙 Time: 10:00–12:00, 18 November
📍 Venue: Alan Turing Institute, British Library
🧭 “𝗧𝗵𝗲 𝗽𝗮𝘀𝘁, 𝗽𝗿𝗲𝘀𝗲𝗻𝘁 𝗮𝗻𝗱 𝗳𝘂𝘁𝘂𝗿𝗲 𝗼𝗳 𝘁𝗵𝗲 𝗨𝗞𝗣 𝗟𝗮𝗯” - 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗶𝗻 𝗖𝗮𝗺𝗯𝗿𝗶𝗱𝗴𝗲
Today, members of the international UKP Lab community gather in Cambridge to reflect on the Lab’s journey over the past two decades and to exchange perspectives on what lies ahead for NLP research.
(1/🧵)
Today, members of the international UKP Lab community gather in Cambridge to reflect on the Lab’s journey over the past two decades and to exchange perspectives on what lies ahead for NLP research.
(1/🧵)
November 17, 2025 at 8:08 AM
🧭 “𝗧𝗵𝗲 𝗽𝗮𝘀𝘁, 𝗽𝗿𝗲𝘀𝗲𝗻𝘁 𝗮𝗻𝗱 𝗳𝘂𝘁𝘂𝗿𝗲 𝗼𝗳 𝘁𝗵𝗲 𝗨𝗞𝗣 𝗟𝗮𝗯” - 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗶𝗻 𝗖𝗮𝗺𝗯𝗿𝗶𝗱𝗴𝗲
Today, members of the international UKP Lab community gather in Cambridge to reflect on the Lab’s journey over the past two decades and to exchange perspectives on what lies ahead for NLP research.
(1/🧵)
Today, members of the international UKP Lab community gather in Cambridge to reflect on the Lab’s journey over the past two decades and to exchange perspectives on what lies ahead for NLP research.
(1/🧵)
𝗙𝗿𝗼𝗺 𝘀𝘁𝗮𝗿𝘁𝘂𝗽 𝗳𝗼𝘂𝗻𝗱𝗲𝗿 𝘁𝗼 𝗦𝗲𝗻𝗶𝗼𝗿 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 𝗮𝘁 𝗠𝗶𝗰𝗿𝗼𝘀𝗼𝗳𝘁 🚀
In this edition of Spotlight on UKP Lab Alumni, we’re featuring Krish Perumal, now a Senior Data Scientist at Microsoft, where he works on applied research in Agentic AI for Microsoft Copilot Studio.
In this edition of Spotlight on UKP Lab Alumni, we’re featuring Krish Perumal, now a Senior Data Scientist at Microsoft, where he works on applied research in Agentic AI for Microsoft Copilot Studio.
November 13, 2025 at 8:39 AM
𝗙𝗿𝗼𝗺 𝘀𝘁𝗮𝗿𝘁𝘂𝗽 𝗳𝗼𝘂𝗻𝗱𝗲𝗿 𝘁𝗼 𝗦𝗲𝗻𝗶𝗼𝗿 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 𝗮𝘁 𝗠𝗶𝗰𝗿𝗼𝘀𝗼𝗳𝘁 🚀
In this edition of Spotlight on UKP Lab Alumni, we’re featuring Krish Perumal, now a Senior Data Scientist at Microsoft, where he works on applied research in Agentic AI for Microsoft Copilot Studio.
In this edition of Spotlight on UKP Lab Alumni, we’re featuring Krish Perumal, now a Senior Data Scientist at Microsoft, where he works on applied research in Agentic AI for Microsoft Copilot Studio.
Reposted by UKP Lab
Misleading content can be both hard to spot and dangerous. But how can we identify and debunk it? Join Professor Iryna Gurevych for the free Milner Prize Lecture on 17 November as she explores:
https://royalsociety.org/science-events-and-lectures/2025/11/how-to-spot-and-debunk-misleading-content/
https://royalsociety.org/science-events-and-lectures/2025/11/how-to-spot-and-debunk-misleading-content/
November 10, 2025 at 4:34 PM
Misleading content can be both hard to spot and dangerous. But how can we identify and debunk it? Join Professor Iryna Gurevych for the free Milner Prize Lecture on 17 November as she explores:
https://royalsociety.org/science-events-and-lectures/2025/11/how-to-spot-and-debunk-misleading-content/
https://royalsociety.org/science-events-and-lectures/2025/11/how-to-spot-and-debunk-misleading-content/
𝗜𝗿𝘆𝗻𝗮 𝗚𝘂𝗿𝗲𝘃𝘆𝗰𝗵 𝘁𝗼 𝗴𝗶𝘃𝗲 𝘁𝗵𝗲 𝟮𝟬𝟮𝟱 𝗠𝗶𝗹𝗻𝗲𝗿 𝗣𝗿𝗶𝘇𝗲 𝗟𝗲𝗰𝘁𝘂𝗿𝗲 𝗮𝘁 𝘁𝗵𝗲 𝗥𝗼𝘆𝗮𝗹 𝗦𝗼𝗰𝗶𝗲𝘁𝘆
We are excited to announce that on 17 November @royalsociety.org will host @igurevych.bsky.social as she gives the Milner Prize Lecture. Her lecture 𝘏𝘰𝘸 𝘵𝘰 𝘚𝘱𝘰𝘵 𝘢𝘯𝘥 𝘋𝘦𝘣𝘶𝘯𝘬 𝘔𝘪𝘴𝘭𝘦𝘢𝘥𝘪𝘯𝘨 𝘊𝘰𝘯𝘵𝘦𝘯𝘵 will also be streamed online.
We are excited to announce that on 17 November @royalsociety.org will host @igurevych.bsky.social as she gives the Milner Prize Lecture. Her lecture 𝘏𝘰𝘸 𝘵𝘰 𝘚𝘱𝘰𝘵 𝘢𝘯𝘥 𝘋𝘦𝘣𝘶𝘯𝘬 𝘔𝘪𝘴𝘭𝘦𝘢𝘥𝘪𝘯𝘨 𝘊𝘰𝘯𝘵𝘦𝘯𝘵 will also be streamed online.
November 12, 2025 at 7:57 AM
𝗜𝗿𝘆𝗻𝗮 𝗚𝘂𝗿𝗲𝘃𝘆𝗰𝗵 𝘁𝗼 𝗴𝗶𝘃𝗲 𝘁𝗵𝗲 𝟮𝟬𝟮𝟱 𝗠𝗶𝗹𝗻𝗲𝗿 𝗣𝗿𝗶𝘇𝗲 𝗟𝗲𝗰𝘁𝘂𝗿𝗲 𝗮𝘁 𝘁𝗵𝗲 𝗥𝗼𝘆𝗮𝗹 𝗦𝗼𝗰𝗶𝗲𝘁𝘆
We are excited to announce that on 17 November @royalsociety.org will host @igurevych.bsky.social as she gives the Milner Prize Lecture. Her lecture 𝘏𝘰𝘸 𝘵𝘰 𝘚𝘱𝘰𝘵 𝘢𝘯𝘥 𝘋𝘦𝘣𝘶𝘯𝘬 𝘔𝘪𝘴𝘭𝘦𝘢𝘥𝘪𝘯𝘨 𝘊𝘰𝘯𝘵𝘦𝘯𝘵 will also be streamed online.
We are excited to announce that on 17 November @royalsociety.org will host @igurevych.bsky.social as she gives the Milner Prize Lecture. Her lecture 𝘏𝘰𝘸 𝘵𝘰 𝘚𝘱𝘰𝘵 𝘢𝘯𝘥 𝘋𝘦𝘣𝘶𝘯𝘬 𝘔𝘪𝘴𝘭𝘦𝘢𝘥𝘪𝘯𝘨 𝘊𝘰𝘯𝘵𝘦𝘯𝘵 will also be streamed online.
📰 𝗙𝗔𝗭 𝗮𝗿𝘁𝗶𝗰𝗹𝗲 𝗯𝘆 𝗜𝗿𝘆𝗻𝗮 𝗚𝘂𝗿𝗲𝘃𝘆𝗰𝗵 𝗮𝗻𝗱 𝗜𝗿𝗶𝗻𝗮 𝗕𝗶𝗴𝗼𝘂𝗹𝗮𝗲𝘃𝗮
The @faznet.bsky.social has published an article by Prof. @igurevych.bsky.social and Irina Bigoulaeva that offers a concise look at where large language models stand today.
(1/🧵)
The @faznet.bsky.social has published an article by Prof. @igurevych.bsky.social and Irina Bigoulaeva that offers a concise look at where large language models stand today.
(1/🧵)
November 7, 2025 at 9:05 AM
📰 𝗙𝗔𝗭 𝗮𝗿𝘁𝗶𝗰𝗹𝗲 𝗯𝘆 𝗜𝗿𝘆𝗻𝗮 𝗚𝘂𝗿𝗲𝘃𝘆𝗰𝗵 𝗮𝗻𝗱 𝗜𝗿𝗶𝗻𝗮 𝗕𝗶𝗴𝗼𝘂𝗹𝗮𝗲𝘃𝗮
The @faznet.bsky.social has published an article by Prof. @igurevych.bsky.social and Irina Bigoulaeva that offers a concise look at where large language models stand today.
(1/🧵)
The @faznet.bsky.social has published an article by Prof. @igurevych.bsky.social and Irina Bigoulaeva that offers a concise look at where large language models stand today.
(1/🧵)
📝 𝗪𝗵𝗮𝘁 𝗮𝘀𝗽𝗲𝗰𝘁𝘀 𝗱𝗼 𝗿𝗲𝘃𝗶𝗲𝘄𝗲𝗿𝘀 𝗳𝗼𝗰𝘂𝘀 𝗼𝗻 𝗶𝗻 𝗽𝗲𝗲𝗿 𝗿𝗲𝘃𝗶𝗲𝘄𝘀?
UKP Lab researchers present a framework for automated aspect analysis that helps to understand how reviewers evaluate papers by identifying criteria such as 𝗡𝗼𝘃𝗲𝗹𝘁𝘆, 𝗦𝗼𝘂𝗻𝗱𝗻𝗲𝘀𝘀, or 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝘃𝗮𝗹𝗶𝗱𝗶𝘁𝘆.
(1/🧵)
UKP Lab researchers present a framework for automated aspect analysis that helps to understand how reviewers evaluate papers by identifying criteria such as 𝗡𝗼𝘃𝗲𝗹𝘁𝘆, 𝗦𝗼𝘂𝗻𝗱𝗻𝗲𝘀𝘀, or 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝘃𝗮𝗹𝗶𝗱𝗶𝘁𝘆.
(1/🧵)
November 4, 2025 at 10:49 AM
📝 𝗪𝗵𝗮𝘁 𝗮𝘀𝗽𝗲𝗰𝘁𝘀 𝗱𝗼 𝗿𝗲𝘃𝗶𝗲𝘄𝗲𝗿𝘀 𝗳𝗼𝗰𝘂𝘀 𝗼𝗻 𝗶𝗻 𝗽𝗲𝗲𝗿 𝗿𝗲𝘃𝗶𝗲𝘄𝘀?
UKP Lab researchers present a framework for automated aspect analysis that helps to understand how reviewers evaluate papers by identifying criteria such as 𝗡𝗼𝘃𝗲𝗹𝘁𝘆, 𝗦𝗼𝘂𝗻𝗱𝗻𝗲𝘀𝘀, or 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝘃𝗮𝗹𝗶𝗱𝗶𝘁𝘆.
(1/🧵)
UKP Lab researchers present a framework for automated aspect analysis that helps to understand how reviewers evaluate papers by identifying criteria such as 𝗡𝗼𝘃𝗲𝗹𝘁𝘆, 𝗦𝗼𝘂𝗻𝗱𝗻𝗲𝘀𝘀, or 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝘃𝗮𝗹𝗶𝗱𝗶𝘁𝘆.
(1/🧵)
𝗧𝗶𝗿𝗲𝗱 𝗼𝗳 𝘆𝗼𝘂𝗿 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗺𝗮𝗸𝗶𝗻𝗴 𝗺𝗮𝗻𝘆 𝗲𝗿𝗿𝗼𝗿𝘀?
➡️ We’ve got the solution!
Meet 𝗦𝗘𝗘𝗘𝗗 🌱 — a framework for 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱 𝗘𝗿𝗿𝗼𝗿 𝗗𝗶𝘀𝗰𝗼𝘃𝗲𝗿𝘆 in conversational AI.
🧩 SEEED detects both 𝗸𝗻𝗼𝘄𝗻 𝗮𝗻𝗱 𝗽𝗿𝗲𝘃𝗶𝗼𝘂𝘀𝗹𝘆 𝘂𝗻𝘀𝗲𝗲𝗻 𝗲𝗿𝗿𝗼𝗿 𝘁𝘆𝗽𝗲𝘀, and even 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗱𝗲𝗳𝗶𝗻𝗶𝘁𝗶𝗼𝗻𝘀 for newly discovered ones.
(1/🧵)
➡️ We’ve got the solution!
Meet 𝗦𝗘𝗘𝗘𝗗 🌱 — a framework for 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱 𝗘𝗿𝗿𝗼𝗿 𝗗𝗶𝘀𝗰𝗼𝘃𝗲𝗿𝘆 in conversational AI.
🧩 SEEED detects both 𝗸𝗻𝗼𝘄𝗻 𝗮𝗻𝗱 𝗽𝗿𝗲𝘃𝗶𝗼𝘂𝘀𝗹𝘆 𝘂𝗻𝘀𝗲𝗲𝗻 𝗲𝗿𝗿𝗼𝗿 𝘁𝘆𝗽𝗲𝘀, and even 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗱𝗲𝗳𝗶𝗻𝗶𝘁𝗶𝗼𝗻𝘀 for newly discovered ones.
(1/🧵)
November 3, 2025 at 7:31 AM
𝗧𝗶𝗿𝗲𝗱 𝗼𝗳 𝘆𝗼𝘂𝗿 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗺𝗮𝗸𝗶𝗻𝗴 𝗺𝗮𝗻𝘆 𝗲𝗿𝗿𝗼𝗿𝘀?
➡️ We’ve got the solution!
Meet 𝗦𝗘𝗘𝗘𝗗 🌱 — a framework for 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱 𝗘𝗿𝗿𝗼𝗿 𝗗𝗶𝘀𝗰𝗼𝘃𝗲𝗿𝘆 in conversational AI.
🧩 SEEED detects both 𝗸𝗻𝗼𝘄𝗻 𝗮𝗻𝗱 𝗽𝗿𝗲𝘃𝗶𝗼𝘂𝘀𝗹𝘆 𝘂𝗻𝘀𝗲𝗲𝗻 𝗲𝗿𝗿𝗼𝗿 𝘁𝘆𝗽𝗲𝘀, and even 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗱𝗲𝗳𝗶𝗻𝗶𝘁𝗶𝗼𝗻𝘀 for newly discovered ones.
(1/🧵)
➡️ We’ve got the solution!
Meet 𝗦𝗘𝗘𝗘𝗗 🌱 — a framework for 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝗱 𝗘𝗿𝗿𝗼𝗿 𝗗𝗶𝘀𝗰𝗼𝘃𝗲𝗿𝘆 in conversational AI.
🧩 SEEED detects both 𝗸𝗻𝗼𝘄𝗻 𝗮𝗻𝗱 𝗽𝗿𝗲𝘃𝗶𝗼𝘂𝘀𝗹𝘆 𝘂𝗻𝘀𝗲𝗲𝗻 𝗲𝗿𝗿𝗼𝗿 𝘁𝘆𝗽𝗲𝘀, and even 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗱𝗲𝗳𝗶𝗻𝗶𝘁𝗶𝗼𝗻𝘀 for newly discovered ones.
(1/🧵)
🤖 𝗛𝗼𝘄 𝗰𝗮𝗻 𝘄𝗲 𝘀𝘁𝗼𝗽 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝗳𝗿𝗼𝗺 𝘁𝗮𝗸𝗶𝗻𝗴 𝘁𝗵𝗲 𝘄𝗿𝗼𝗻𝗴 𝗮𝗰𝘁𝗶𝗼𝗻—𝙗𝙚𝙛𝙤𝙧𝙚 𝙞𝙩 𝙝𝙖𝙥𝙥𝙚𝙣𝙨?
Imagine your shopping agent accidentally buying something expensive you didn’t want! 💸 #InferAct keeps your AI agents reliable and safe by rectifying misaligned actions 𝗯𝗲𝗳𝗼𝗿𝗲 they occur🧠✅
(1/🧵)
Imagine your shopping agent accidentally buying something expensive you didn’t want! 💸 #InferAct keeps your AI agents reliable and safe by rectifying misaligned actions 𝗯𝗲𝗳𝗼𝗿𝗲 they occur🧠✅
(1/🧵)
October 31, 2025 at 9:47 AM
🤖 𝗛𝗼𝘄 𝗰𝗮𝗻 𝘄𝗲 𝘀𝘁𝗼𝗽 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝗳𝗿𝗼𝗺 𝘁𝗮𝗸𝗶𝗻𝗴 𝘁𝗵𝗲 𝘄𝗿𝗼𝗻𝗴 𝗮𝗰𝘁𝗶𝗼𝗻—𝙗𝙚𝙛𝙤𝙧𝙚 𝙞𝙩 𝙝𝙖𝙥𝙥𝙚𝙣𝙨?
Imagine your shopping agent accidentally buying something expensive you didn’t want! 💸 #InferAct keeps your AI agents reliable and safe by rectifying misaligned actions 𝗯𝗲𝗳𝗼𝗿𝗲 they occur🧠✅
(1/🧵)
Imagine your shopping agent accidentally buying something expensive you didn’t want! 💸 #InferAct keeps your AI agents reliable and safe by rectifying misaligned actions 𝗯𝗲𝗳𝗼𝗿𝗲 they occur🧠✅
(1/🧵)
🎙️ “𝗙𝗿𝗼𝗺 𝗔𝗹𝗴𝗼𝗿𝗶𝘁𝗵𝗺𝘀 𝘁𝗼 𝗜𝗻𝘁𝘂𝗶𝘁𝗶𝗼𝗻 – 𝗪𝗵𝗮𝘁 𝗔𝗜 𝗖𝗮𝗻 𝗟𝗲𝗮𝗿𝗻 𝗳𝗿𝗼𝗺 𝗛𝘂𝗺𝗮𝗻 𝗥𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴”
Prof. @igurevych.bsky.social, Director of the UKP Lab at @tuda.bsky.social and Academic Fellow of the @zuseschooleliza.bsky.social, took part in an interdisciplinary panel at the #DAAD Zuse Schools Herbst Event 2025.
(1/🧵)
Prof. @igurevych.bsky.social, Director of the UKP Lab at @tuda.bsky.social and Academic Fellow of the @zuseschooleliza.bsky.social, took part in an interdisciplinary panel at the #DAAD Zuse Schools Herbst Event 2025.
(1/🧵)
October 30, 2025 at 1:53 PM
🎙️ “𝗙𝗿𝗼𝗺 𝗔𝗹𝗴𝗼𝗿𝗶𝘁𝗵𝗺𝘀 𝘁𝗼 𝗜𝗻𝘁𝘂𝗶𝘁𝗶𝗼𝗻 – 𝗪𝗵𝗮𝘁 𝗔𝗜 𝗖𝗮𝗻 𝗟𝗲𝗮𝗿𝗻 𝗳𝗿𝗼𝗺 𝗛𝘂𝗺𝗮𝗻 𝗥𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴”
Prof. @igurevych.bsky.social, Director of the UKP Lab at @tuda.bsky.social and Academic Fellow of the @zuseschooleliza.bsky.social, took part in an interdisciplinary panel at the #DAAD Zuse Schools Herbst Event 2025.
(1/🧵)
Prof. @igurevych.bsky.social, Director of the UKP Lab at @tuda.bsky.social and Academic Fellow of the @zuseschooleliza.bsky.social, took part in an interdisciplinary panel at the #DAAD Zuse Schools Herbst Event 2025.
(1/🧵)
𝗪𝗵𝗲𝗻 𝗮𝗻 𝗟𝗟𝗠’𝘀 𝗼𝘄𝗻 𝗹𝗼𝗴𝗶𝗰 𝗯𝗲𝗰𝗼𝗺𝗲𝘀 𝗶𝘁𝘀 𝗯𝗶𝗴𝗴𝗲𝘀𝘁 𝘄𝗲𝗮𝗸𝗻𝗲𝘀𝘀 😧
Researchers at UKP Lab introduce #POATE, a jailbreak technique that exploits contrastive reasoning to bypass safety mechanisms in large language models.
(1/🧵)
Researchers at UKP Lab introduce #POATE, a jailbreak technique that exploits contrastive reasoning to bypass safety mechanisms in large language models.
(1/🧵)
October 30, 2025 at 8:43 AM
𝗪𝗵𝗲𝗻 𝗮𝗻 𝗟𝗟𝗠’𝘀 𝗼𝘄𝗻 𝗹𝗼𝗴𝗶𝗰 𝗯𝗲𝗰𝗼𝗺𝗲𝘀 𝗶𝘁𝘀 𝗯𝗶𝗴𝗴𝗲𝘀𝘁 𝘄𝗲𝗮𝗸𝗻𝗲𝘀𝘀 😧
Researchers at UKP Lab introduce #POATE, a jailbreak technique that exploits contrastive reasoning to bypass safety mechanisms in large language models.
(1/🧵)
Researchers at UKP Lab introduce #POATE, a jailbreak technique that exploits contrastive reasoning to bypass safety mechanisms in large language models.
(1/🧵)
🚀 𝗝𝗼𝗶𝗻 𝘁𝗵𝗲 𝗭𝘂𝘀𝗲 𝗦𝗰𝗵𝗼𝗼𝗹 𝗘𝗟𝗜𝗭𝗔 𝗶𝗻 𝗗𝗮𝗿𝗺𝘀𝘁𝗮𝗱𝘁!
Interested in world-class research? Please apply and indicate your interest to join the team of @ukplab.bsky.social at @tuda.bsky.social, led by Prof. @igurevych.bsky.social.
🔗 www.tu-darmstadt.de/forschen/for...
📍 Location: Darmstadt
🗓️ Start: 01.01.2026
Interested in world-class research? Please apply and indicate your interest to join the team of @ukplab.bsky.social at @tuda.bsky.social, led by Prof. @igurevych.bsky.social.
🔗 www.tu-darmstadt.de/forschen/for...
📍 Location: Darmstadt
🗓️ Start: 01.01.2026
ELIZA
The Konrad Zuse School of Excellence in Learning and Intelligent Systems (ELIZA) is a graduate school in the field of artificial intelligence (AI) funded by the German Academic Exchange Service (DAAD)...
www.tu-darmstadt.de
October 27, 2025 at 9:34 AM
🚀 𝗝𝗼𝗶𝗻 𝘁𝗵𝗲 𝗭𝘂𝘀𝗲 𝗦𝗰𝗵𝗼𝗼𝗹 𝗘𝗟𝗜𝗭𝗔 𝗶𝗻 𝗗𝗮𝗿𝗺𝘀𝘁𝗮𝗱𝘁!
Interested in world-class research? Please apply and indicate your interest to join the team of @ukplab.bsky.social at @tuda.bsky.social, led by Prof. @igurevych.bsky.social.
🔗 www.tu-darmstadt.de/forschen/for...
📍 Location: Darmstadt
🗓️ Start: 01.01.2026
Interested in world-class research? Please apply and indicate your interest to join the team of @ukplab.bsky.social at @tuda.bsky.social, led by Prof. @igurevych.bsky.social.
🔗 www.tu-darmstadt.de/forschen/for...
📍 Location: Darmstadt
🗓️ Start: 01.01.2026
🤝 𝗦𝗲𝗻𝘁𝗲𝗻𝗰𝗲 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀 𝗷𝗼𝗶𝗻𝘀 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗙𝗮𝗰𝗲
Originally developed at the UKP Lab at @tuda.bsky.social, Sentence Transformers has become one of the world’s most widely used open-source libraries for semantic embeddings in natural language processing.
(1/🧵)
Originally developed at the UKP Lab at @tuda.bsky.social, Sentence Transformers has become one of the world’s most widely used open-source libraries for semantic embeddings in natural language processing.
(1/🧵)
October 22, 2025 at 2:08 PM
🤝 𝗦𝗲𝗻𝘁𝗲𝗻𝗰𝗲 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗲𝗿𝘀 𝗷𝗼𝗶𝗻𝘀 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗙𝗮𝗰𝗲
Originally developed at the UKP Lab at @tuda.bsky.social, Sentence Transformers has become one of the world’s most widely used open-source libraries for semantic embeddings in natural language processing.
(1/🧵)
Originally developed at the UKP Lab at @tuda.bsky.social, Sentence Transformers has become one of the world’s most widely used open-source libraries for semantic embeddings in natural language processing.
(1/🧵)
🚀 Apply now for a PhD with the new RAI – Reasonable Artificial Intelligence Cluster of Excellence!
Join top German universities exploring Active, Challenging, Observational & Systemic AI.
💡 Deadline: Nov 16, 2025
🔗 hessian.ai/projects/rea...
#AI #PhD #Research #MachineLearning #Germany
Join top German universities exploring Active, Challenging, Observational & Systemic AI.
💡 Deadline: Nov 16, 2025
🔗 hessian.ai/projects/rea...
#AI #PhD #Research #MachineLearning #Germany
October 21, 2025 at 12:55 PM
🚀 Apply now for a PhD with the new RAI – Reasonable Artificial Intelligence Cluster of Excellence!
Join top German universities exploring Active, Challenging, Observational & Systemic AI.
💡 Deadline: Nov 16, 2025
🔗 hessian.ai/projects/rea...
#AI #PhD #Research #MachineLearning #Germany
Join top German universities exploring Active, Challenging, Observational & Systemic AI.
💡 Deadline: Nov 16, 2025
🔗 hessian.ai/projects/rea...
#AI #PhD #Research #MachineLearning #Germany
🚀 New paper out in TMLR!
“Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning”
📃 Paper: openreview.net/forum?id=10Q...
💻 Code: github.com/UKPLab/tmlr2...
“Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning”
📃 Paper: openreview.net/forum?id=10Q...
💻 Code: github.com/UKPLab/tmlr2...
October 15, 2025 at 7:59 AM
🚀 New paper out in TMLR!
“Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning”
📃 Paper: openreview.net/forum?id=10Q...
💻 Code: github.com/UKPLab/tmlr2...
“Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning”
📃 Paper: openreview.net/forum?id=10Q...
💻 Code: github.com/UKPLab/tmlr2...
🧠 AI with Confidentiality: A Privacy Roadmap for Mental Health
New publication in Nature Computational Science ✨
Mental health data is among the most sensitive information people share. How can AI support diagnosis and therapy without compromising privacy?
New publication in Nature Computational Science ✨
Mental health data is among the most sensitive information people share. How can AI support diagnosis and therapy without compromising privacy?
October 13, 2025 at 12:12 PM
🧠 AI with Confidentiality: A Privacy Roadmap for Mental Health
New publication in Nature Computational Science ✨
Mental health data is among the most sensitive information people share. How can AI support diagnosis and therapy without compromising privacy?
New publication in Nature Computational Science ✨
Mental health data is among the most sensitive information people share. How can AI support diagnosis and therapy without compromising privacy?
🚀 𝗟𝗮𝘁𝗲𝘀𝘁 𝗣𝗲𝗲𝗿 𝗥𝗲𝘃𝗶𝗲𝘄 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝗥𝗲𝗹𝗲𝗮𝘀𝗲 𝗳𝗿𝗼𝗺 𝗔𝗥𝗥 𝟮𝟬𝟮𝟱!
tudatalib.ulb.tu-darmstadt.de/handle/tudat...
📊 𝗡𝗲𝘄𝗹𝘆 𝗮𝗱𝗱𝗲𝗱 𝗔𝗖𝗟 𝟮𝟬𝟮𝟱 𝗱𝗮𝘁𝗮:
✅ 𝟮𝗸 papers
✅ 𝟮𝗸 reviews
✅ 𝟴𝟰𝟵 meta-reviews
✅ 𝟭.𝟱𝗸 papers with rebuttals
(1/🧵)
tudatalib.ulb.tu-darmstadt.de/handle/tudat...
📊 𝗡𝗲𝘄𝗹𝘆 𝗮𝗱𝗱𝗲𝗱 𝗔𝗖𝗟 𝟮𝟬𝟮𝟱 𝗱𝗮𝘁𝗮:
✅ 𝟮𝗸 papers
✅ 𝟮𝗸 reviews
✅ 𝟴𝟰𝟵 meta-reviews
✅ 𝟭.𝟱𝗸 papers with rebuttals
(1/🧵)
October 8, 2025 at 6:58 AM
🚀 𝗟𝗮𝘁𝗲𝘀𝘁 𝗣𝗲𝗲𝗿 𝗥𝗲𝘃𝗶𝗲𝘄 𝗗𝗮𝘁𝗮𝘀𝗲𝘁 𝗥𝗲𝗹𝗲𝗮𝘀𝗲 𝗳𝗿𝗼𝗺 𝗔𝗥𝗥 𝟮𝟬𝟮𝟱!
tudatalib.ulb.tu-darmstadt.de/handle/tudat...
📊 𝗡𝗲𝘄𝗹𝘆 𝗮𝗱𝗱𝗲𝗱 𝗔𝗖𝗟 𝟮𝟬𝟮𝟱 𝗱𝗮𝘁𝗮:
✅ 𝟮𝗸 papers
✅ 𝟮𝗸 reviews
✅ 𝟴𝟰𝟵 meta-reviews
✅ 𝟭.𝟱𝗸 papers with rebuttals
(1/🧵)
tudatalib.ulb.tu-darmstadt.de/handle/tudat...
📊 𝗡𝗲𝘄𝗹𝘆 𝗮𝗱𝗱𝗲𝗱 𝗔𝗖𝗟 𝟮𝟬𝟮𝟱 𝗱𝗮𝘁𝗮:
✅ 𝟮𝗸 papers
✅ 𝟮𝗸 reviews
✅ 𝟴𝟰𝟵 meta-reviews
✅ 𝟭.𝟱𝗸 papers with rebuttals
(1/🧵)
✨ Exciting news from the #QNLP Conference 2025 in Bloomington, Indiana!
@akatief.bsky.social gave a talk on “An Efficient Quantum Classifier Based on Hamiltonian Representations” — exploring how quantum computing can open new frontiers for natural language processing.
(1/🧵)
@akatief.bsky.social gave a talk on “An Efficient Quantum Classifier Based on Hamiltonian Representations” — exploring how quantum computing can open new frontiers for natural language processing.
(1/🧵)
October 2, 2025 at 7:31 AM
✨ Exciting news from the #QNLP Conference 2025 in Bloomington, Indiana!
@akatief.bsky.social gave a talk on “An Efficient Quantum Classifier Based on Hamiltonian Representations” — exploring how quantum computing can open new frontiers for natural language processing.
(1/🧵)
@akatief.bsky.social gave a talk on “An Efficient Quantum Classifier Based on Hamiltonian Representations” — exploring how quantum computing can open new frontiers for natural language processing.
(1/🧵)
👉 Interested in working on AI for mental health? This is a 𝗺𝘂𝘀𝘁-𝗿𝗲𝗮𝗱 𝘀𝗶𝗻𝗰𝗲 𝘁𝗵𝗲 𝗱𝗮𝘁𝗮 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗶𝘀 𝗮 𝗺𝗮𝗷𝗼𝗿 𝗯𝗼𝘁𝘁𝗹𝗲𝗻𝗲𝗰𝗸!
Our survey maps the mental health dataset landscape, covering a wide range of disorders, tasks, modalities, accessibility, synthetic data, and cultural reach.
(1/🧵)
Our survey maps the mental health dataset landscape, covering a wide range of disorders, tasks, modalities, accessibility, synthetic data, and cultural reach.
(1/🧵)
October 1, 2025 at 7:17 AM
👉 Interested in working on AI for mental health? This is a 𝗺𝘂𝘀𝘁-𝗿𝗲𝗮𝗱 𝘀𝗶𝗻𝗰𝗲 𝘁𝗵𝗲 𝗱𝗮𝘁𝗮 𝗮𝘃𝗮𝗶𝗹𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗶𝘀 𝗮 𝗺𝗮𝗷𝗼𝗿 𝗯𝗼𝘁𝘁𝗹𝗲𝗻𝗲𝗰𝗸!
Our survey maps the mental health dataset landscape, covering a wide range of disorders, tasks, modalities, accessibility, synthetic data, and cultural reach.
(1/🧵)
Our survey maps the mental health dataset landscape, covering a wide range of disorders, tasks, modalities, accessibility, synthetic data, and cultural reach.
(1/🧵)
🚀 𝗞𝗲𝘆𝗻𝗼𝘁𝗲 𝗯𝘆 𝗣𝗿𝗼𝗳. 𝗜𝗿𝘆𝗻𝗮 𝗚𝘂𝗿𝗲𝘃𝘆𝗰𝗵 𝗶𝗻 𝗟𝗷𝘂𝗯𝗹𝗷𝗮𝗻𝗮
Prof. @igurevych.bsky.social, Head of the UKP Lab, is giving a keynote today at the 28th International Conference on Discovery Science 2025 in Ljubljana.
Prof. @igurevych.bsky.social, Head of the UKP Lab, is giving a keynote today at the 28th International Conference on Discovery Science 2025 in Ljubljana.
September 25, 2025 at 7:36 AM
🚀 𝗞𝗲𝘆𝗻𝗼𝘁𝗲 𝗯𝘆 𝗣𝗿𝗼𝗳. 𝗜𝗿𝘆𝗻𝗮 𝗚𝘂𝗿𝗲𝘃𝘆𝗰𝗵 𝗶𝗻 𝗟𝗷𝘂𝗯𝗹𝗷𝗮𝗻𝗮
Prof. @igurevych.bsky.social, Head of the UKP Lab, is giving a keynote today at the 28th International Conference on Discovery Science 2025 in Ljubljana.
Prof. @igurevych.bsky.social, Head of the UKP Lab, is giving a keynote today at the 28th International Conference on Discovery Science 2025 in Ljubljana.
🔁 Prof. Iryna Gurevych, Director of the UKP Lab at TU Darmstadt, is featured in this ATHENE video portrait.
🎥 The video (in German) introduces her research on disinformation and cognitive security, where methods from #NLP intersect with questions of #cybersecurity.
⬇️ Watch the video portrait here
🎥 The video (in German) introduces her research on disinformation and cognitive security, where methods from #NLP intersect with questions of #cybersecurity.
⬇️ Watch the video portrait here
👤 Watch our video portrait about ATHENE Principal Investigator and renowned computer scientist Prof. @igurevych.bsky.social @tuda.bsky.social @ukplab.bsky.social!
🎞️To the portrait: www.youtube.com/watch?v=j3Or...
🎞️ The trailer highlights her research on #disinformation and cognitive security:
🎞️To the portrait: www.youtube.com/watch?v=j3Or...
🎞️ The trailer highlights her research on #disinformation and cognitive security:
August 27, 2025 at 9:34 AM
🔁 Prof. Iryna Gurevych, Director of the UKP Lab at TU Darmstadt, is featured in this ATHENE video portrait.
🎥 The video (in German) introduces her research on disinformation and cognitive security, where methods from #NLP intersect with questions of #cybersecurity.
⬇️ Watch the video portrait here
🎥 The video (in German) introduces her research on disinformation and cognitive security, where methods from #NLP intersect with questions of #cybersecurity.
⬇️ Watch the video portrait here
Fail to utilize LLM-as-a-judge systems for evaluating expert writing tasks?🤔
They often don’t know what to judge (missing expert criteria) and don’t know how to judge (lacking structured evaluation). In our new paper, we integrate task-specific criteria with expert preferences. 🚀
(1/🧵)
They often don’t know what to judge (missing expert criteria) and don’t know how to judge (lacking structured evaluation). In our new paper, we integrate task-specific criteria with expert preferences. 🚀
(1/🧵)
August 26, 2025 at 9:28 AM
Fail to utilize LLM-as-a-judge systems for evaluating expert writing tasks?🤔
They often don’t know what to judge (missing expert criteria) and don’t know how to judge (lacking structured evaluation). In our new paper, we integrate task-specific criteria with expert preferences. 🚀
(1/🧵)
They often don’t know what to judge (missing expert criteria) and don’t know how to judge (lacking structured evaluation). In our new paper, we integrate task-specific criteria with expert preferences. 🚀
(1/🧵)