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 Flagship Project in Cardiology and AI is Featured in the News!

Archimedes Flagship Project in Cardiology and AI is Featured in the News!

30 September 2025

Archimedes Research Unit of the Athena Research Center, Greece, is featured in a recent article in Dnews. This article is about an Archimedes flagship project in cardiology and AI that aims to use "two-dimensional echocardiographic data to develop deep learning tools and improve the treatment of heart problems."

Best Paper Award at FAIEMA 202

Best Paper Award at FAIEMA 202

29 September 2025

Vasileios Moustakas, PhD student at the School of Electrical and Computer Engineering - NTUA and Academic Fellow at Archimedes, Athena Research Center, Greece, Konstantinos Cheliotis and Anna Mylona, both MEng students at the School of Electrical and Computer Engineering - NTUA and interns at Archimedes, Athena Research Center, Vassilis Alimisis, Postdoctoral Researcher at Archimedes, Athena Research Center, and Paul Sotiriadis, Lead Researcher at Archimedes, Athena Research Center, and a Professor at the School of Electrical and Computer Engineering - NTUA, received the Best Paper Award (PhD Symposium) at the

Nature Communications Publication on Advanced AI in Biological Research by Giorgos Papanastasiou

Nature Communications Publication on Advanced AI in Biological Research by Giorgos Papanastasiou

25 September 2025

Giorgos Papanastasiou, Lead Researcher at the Archimedes Research Unit of the Athena Research Center, Greece,and Faculty Research Fellow at Edinburgh Imaging, at the University of Edinburgh, the Queen’s Medical Research Institute, Edinburgh, UK, has co-published a Nature Communications paper on "Clinical implications of bone marrow adiposity identified by phenome-wide association and Mendelian randomization in the UK Biobank."Prof. Papanastasiou mentions that "this project is a strong testament to the power of augmenting biological research with advanced AI and data science methods."

More news items here
 
 

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)