archimedes-Artificial Intelligence, Data Science, Algorithms-greece

 
Artificial Intelligence
 
Data Science
 
Algorithms

[Archimedes NLP Group Invited Talk]Understanding the Trade-Offs Between Hallucinations and Mode Collapse in Language Generation

Dates
2025-01-15 14:30 - 16:00
Venue
Artemidos 1 - Amphitheater
TITLE: Understanding the Trade-Offs Between Hallucinations and Mode Collapse in Language Generation

SPEAKER: Grigoris Velegkas(Yale University, USA)

ABSTRACT: Specifying all desirable properties of a language model is challenging, but certain requirements seem essential. Given samples from an unknown language, the trained model should produce valid strings not seen in the training set, and be expressive enough to capture the language's full breadth. Otherwise, outputting invalid strings constitutes "hallucination," and failing to capture the full breadth leads to "mode collapse." Recent work by Kleinberg and Mullainathan [KM24], building on classical work on the closely related problem of language identification by Gold [Gol67] and Angluin [Ang79, 80], provides a concrete mathematical framework to study the problem of language generation. Kleinberg and Mullainathan showed that for all countable collections of languages, it is possible to create a language model that does not hallucinate but suffers from mode collapse. They asked whether this tension between validity and breadth is inherent for language generation.

In this talk, we define various notions of breadth for language generation, and completely characterize when generation with validity and breadth is possible under each of these notions. Our results answer the question of [KM24] and show that this tension between validity and breadth is indeed inherent for language generation. Moreover, we formalize the notion of stable generation, a natural requirement derived from Gold’s work [Gold67], and discuss when this type of generation is achievable. Finally, we discuss the implications of our results in the universal rates setting of Bousquet, Hanneke, Moran, van Handel, and Yehudayoff [BGMvY21]. The talk is based on joint works with Alkis Kalavasis and Anay Mehrotra.

References:  https://arxiv.org/abs/2411.09642 , https://arxiv.org/abs/2412.18530 

SHORT BIO: Grigoris Velegkas is a final-year PhD student in Computer Science at Yale University, working with Prof. Amin Karbasi. Before that, he studied Electrical and Computer Engineering at the National Technical University of Athens, where he worked with Prof. Dimitris Fotakis. His research lies at the intersection of machine learning and theoretical computer science, and focuses on three main directions: i) understanding generalization properties of ML algorithms, ii) exploring responsible use of ML systems and designing algorithms with provable replicability guarantees, and iii) understanding the interaction between ML algorithms and mechanisms. He was a research intern at Google Research in summer 2023 and summer 2024, and a student researcher from October 2023 to May 2024.


________________________________________________________________________________
Microsoft Teams Need help?
Meeting ID: 364 928 182 762
Passcode: w24fHy
________________________________________________________________________________

 
 

Vision

To position Greece as a leading player in AI and Data Science

image
image

Mission

To build an AI Excellence Hub in Greece where the international research community can connect, groundbreaking ideas can thrive, and the next generation of scientists emerges, shaping a brighter future for Greece and the world

 

Welcome to ARCHIMEDES, a vibrant research hub connecting the global AI and Data Science research community fostering groundbreaking research in Greece and beyond. Its dedicated core team, comprising lead researchers, affiliated researchers, Post-Docs, PhDs and interns, is committed to advancing basic and applied research in Artificial Intelligence and its supporting disciplines, including Algorithms, Statistics, Learning Theory, and Game Theory organized around 8 core research areas. By collaborating with Greek and Foreign Universities and Research Institutes, ARCHIMEDES disseminates its research findings fostering knowledge exchange and providing enriching opportunities for students. Leveraging AI to address real-world challenges, ARCHIMEDES promotes innovation within the Greek ecosystem and extends its societal impact. Established in January 2022, as a research unit of the Athena Research Center with support from the Committee Greece 2021, ARCHIMEDES is funded for its first four years by the EU Recovery and Resilience Facility (RRF).

 
 

NEWS

 
Archimedes and the Biomedical Research Foundation Share Latest Findings in AI and Medicine

Archimedes and the Biomedical Research Foundation Share Latest Findings in AI and Medicine

Archimedes and the Biomedical Research Foundation of the Academy of Athens successfully hosted a special collaborative session at the Panhellenic Working Group Seminars of the Hellenic Society of Cardiology. This session focused on innovative applications of artificial intelligence in medicine, with a particular emphasis on advancements in cardiology. Held on Friday, February 7, 2025, in Room MC2 of the Megaron Athens International Conference Centre, the event brought together leading experts to explore how artificial intelligence is transforming cardiovascular medicine.

Archimedes Reaches Milestone of 200 Publications

Archimedes Reaches Milestone of 200 Publications

Archimedes is proud to announce that its researchers have published over 200 scientific publications in top-tier conferences (NeurIPS, ICLR, ICML) and journals.Archimedes maintains a vibrant scientific community of over 130 researchers, including more than 60 senior researchers (faculty members from Greece and abroad), 12 postdoctoral fellows, and 55 PhD students, along with over 20 undergraduate interns from various disciplines.

Happy International Greek Language Day!

Happy International Greek Language Day!

Today, we celebrate the historical, cultural, and linguistic significance of the Greek language. While Standard Modern Greek often takes center stage, we at Archimedes - AI and Data Science Research Hub recognize the impressive diversity and great cultural significance of its numerous dialects. These dialects present both exciting opportunities and complex challenges for AI and Large Language Models (LLMs) because each one of them presents unique linguistic features and all of them are low resourced. That’s why we’re using cutting-edge AI to document, digitize, and analyze these invaluable linguistic treasures, ensuring their preservation and accessibility for generations to come.

Two Research Positions in Data Stream Management Systems & Big Data Management

Two Research Positions in Data Stream Management Systems & Big Data Management

We are pleased to announce the availability of two research positions in data stream management systems and big data management, to be co-supervised by Assistant Professor Odysseas Papapetrou from the Eindhoven University of Technology (TU/e) in the Netherlands and Professor Minos Garofalakis from the Technical University of Crete in Greece.

 
 

The project “ARCHIMEDES Unit: Research in Artificial Intelligence, Data Science and Algorithms” with code OPS 5154714 is implemented by the National Recovery and Resilience Plan “Greece 2.0” and is funded by the European Union – NextGenerationEU.

greece2.0 eu_arch_logo_en

 

Stay connected! Subscribe to our mailing list by emailing sympa@lists.athenarc.gr
with the subject "subscribe archimedes-news Firstname LastName"
(replace with your details)