Message-ID: <dada9475-af9a-414a-ad8a-edcae3f5ff45@mi.parisdescartes.fr>
Date: Fri, 15 Mar 2024 02:07:20 +0100
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
From: Themis Palpanas <themis@mi.parisdescartes.fr>
Content-Language: en-US, fr
Organization: Universite Paris Cite
To: Themis Palpanas <themis@mi.parisdescartes.fr>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Subject: [newsletter.diip] Apr3 4pmParis, diiP Distinguished Lecture:
 Alessandro Moschitti, Retrieval Augmented Generative Question Answering
 for Personal Assistants
Reply-To: newsletter.diip@listes.u-paris.fr
Errors-To: newsletter.diip-owner@listes.u-paris.fr
Precedence: list
Precedence: bulk
Sender: newsletter.diip-request@listes.u-paris.fr
Archived-At: <https://listes.u-paris.fr/wws/arcsearch_id/newsletter.diip/2024-03/dada9475-af9a-414a-ad8a-edcae3f5ff45%40mi.parisdescartes.fr>


Distinguished Lecture Series
Data Intelligence Institute of Paris (diiP)
<https://u-paris.fr/diip/>
-------------------------------------------


Who: Dr. Alessandro Moschitti (Amazon)
When: April 3, 2024, at 4pmParis
Where: Online (Zoom):
<https://u-paris.zoom.us/j/85080755487?pwd=dFU1OERva2VvR0tXSnFsZHU4clljUT09>

title:
Retrieval Augmented Generative Question Answering for Personal Assistants

abstract:
Recent work has shown that Large Language Models (LLMs) can potentially 
answer any question with high accuracy, also providing justifications of 
the provided output. At the same time, other research work has shown 
that even the most powerful and accurate models, such as ChatGPT 4, 
generate hallucinations, which often invalidated their answers. 
Retrieval-augmented LLMs are currently a practical solution that can 
effectively solve the above-mentioned problem. However, the quality of 
grounding is essential in order to improve the model, since noisy 
context deteriorates the overall performance. In this talk, after we 
introduce LLMs and Question Answering (QA), and we will present our 
experience with Generative QA, which uses basic search engines and 
accurate passage rerankers to augment relatively small language models. 
We will provide a different but more direct interpretation of retrieval 
augmented LLMs and contextual grounding. Finally, we will show our 
latest techniques for Reinforcement Learning from Human Feedback 
proposed for fine-tuning LLMs that we developed in contemporary with the 
main stream effort of OpenAI.

short bio:
Alessandro Moschitti is a Principal Research Scientist of Amazon Alexa, 
where he has been leading the science of Alexa information service since 
2018. He designed the Alexa Question Answering (QA) system based on 
unstructured text and more recently the first Generative QA system, 
which extends the answering skills of Alexa. He obtained his Ph.D. in CS 
from the University of Rome in 2003, and then did his postdoc at The 
University of Texas at Dallas for two years. He was professor of the CS 
Dept. of the University of Trento, Italy, from 2007 to 2021. He 
participated to the Jeopardy! Grand Challenge with the IBM Watson 
Research center (2009 to 2011), and collaborated with them until 2015. 
He was a Principal Scientist of the Qatar Computing Research Institute 
(QCRI) for five years (2013-2018). His expertise concerns theoretical 
and applied machine learning in the areas of NLP, IR and Data Mining. He 
is well-known for his work on structural kernels and neural networks for 
syntactic/semantic inference over text, documented by around 350 
scientific articles. He has received four IBM Faculty Awards, one Google 
Faculty Award, and five best paper awards. He was the General Chair of 
EACL 2023 and EMNLP 2014, a PC co-Chair of CoNLL 2015, and has had a 
chair role in more than 70 conferences and workshops. He is currently a 
senior action/associate editor of ACM Computing Survey and JAIR. He has 
led ~30 research projects, e.g., a 5-year research project with MIT CSAIL.




-- 
---------------------------------------------------------
   Distinguished Prof. Themis Palpanas
   Senior Member of the French University Institute (IUF)
   Director of Data Intelligence Institute of Paris (diiP)
   Director of LIPADE (Computer Science dept.)
   http://www.mi.parisdescartes.fr/~themisp/

   LIPADE - University Paris Cite
   45 Rue Des Saints-Peres
   Paris 75006, France

   tel:   +33-1-7653-0365
---------------------------------------------------------