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 Talk by Alexandra Meliou on

Archimedes Talk by Alexandra Meliou on "Data Analysis and Manipulation through a Constrained Optimization Lens"

On Tuesday 4 November, 2025, from 1:00 pm to 2:00 pm, at the Archimedes Amphitheatre (1 Artemidos Street, 15125, Marousi, Archimedes, Athena Research Center, Greece), Professor Alexandra Meliou, Professor at the College of Information and Computer Sciences at the University of Massachusetts Amherst, USA, and a visiting researcher at the Archimedes Research Center, Athena Research Center, Greece, will deliver an Archimedes talk on "Data Analysis and Manipulation through a Constrained Optimization Lens."

Exploring the Frontiers of AI and Biomechanics at ICIST 2025

Exploring the Frontiers of AI and Biomechanics at ICIST 2025

Archimedes, Athena Research Center, Greece is happy to see its work being featured at the 15th International Conference on Information Society and Technology (ICIST 2025), at Kaunas University of Technology, Lithuania, through an invited keynote speech by Dr. Serafeim Moustakidis, titled: “Bringing Biomechanics into the AI Era: A New Frontier for Gait and Joint Health.”

Archimedes Talk by Manos Athanassoulis on

Archimedes Talk by Manos Athanassoulis on "Harnessing the Untapped Benefits of Near-Sortedness for Data Systems"

On Tuesday 21 October, 2025, from 1:00 pm to 2:00 pm, at the Archimedes Amphitheatre (1 Artemidos Street, 15125, Marousi, Archimedes, Athena Research Center, Greece), Professor Manos Athanassoulis, Associate Professor of Computer Science at Boston University (BU), USA, Director and Founder of the BU Data-intensive Systems and Computing Laboratory, BU, USA, and Co-Director of the BU Massive Data Algorithms and Systems Group, BU, USA, will deliver an Archimedes talk on "Harnessing the Untapped Benefits of Near-Sortedness for Data Systems."

GameSec 2025 just Around the Corner!

GameSec 2025 just Around the Corner!

The 16th Conference on Game Theory and AI for Security (GameSec25), an event strongly supported by Archimedes, Athena Research Center, Greece will take place at the National Technical University of Athens, Greece from October 13-15 2025. "With the rapid advancement of artificial intelligence, game theory, and security technologies, the resilience and trustworthiness of modern systems is more critical than ever. The 2025 Conference on Game Theory and AI for Security focuses on leveraging strategic decision-making, adversarial reasoning, and computational intelligence to address security challenges in complex and dynamic environments.

11 Papers Accepted at NeurIPS 2025!

11 Papers Accepted at NeurIPS 2025!

We are happy to announce that 11 papers from Archimedes, Athena Research Center, Greece, have been accepted at the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)!NeurIPS is a major annual event in the artificial intelligence and machine learning community and this year it will take place from December 2 to December 7 at the San Diego Convention Center, California, USA.

 
 

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)