LightOn Unlocks Agentic RAG with new SOTA Model Reason-ModernColBERT

DJ LightOn Unlocks Agentic RAG with new SOTA Model Reason-ModernColBERT

LIGHTON 
LightOn Unlocks Agentic RAG with new SOTA Model Reason-ModernColBERT 
22-May-2025 / 18:15 CET/CEST 
Dissemination of a French Regulatory News, transmitted by EQS Group. 
The issuer is solely responsible for the content of this announcement. 
=---------------------------------------------------------------------------------------------------------------------- 
 
 
Press Release 
Paris, May 22, 2025 
 
LightOn Unlocks Agentic RAG with new SOTA Model Reason-ModernColBERT 
 
 
 
 
After the recent release of GTE-ModernColBERT exhibiting state-of-the-art results on long-context retrieval, LightOn 
announces a major leap forward in AI-driven knowledge discovery: Reason-ModernColBERT, an open-source multi-vector 
model purpose-built for Deep Research applications. 
Redefining Retrieval: From Matching to Reasoning 
 
Source: BRIGHT: a realistic and challenging benchmark for reasoning-intensive retrieval 
 
With the rise of Deep Research, organizations are demanding more than simple lexical or semantic matching. Today's 
cutting-edge enterprise insights require reasoning, the ability to connect, synthesize, and uncover knowledge beyond 
what's explicitly stated. 
Recent advancements in Large Language Models have sparked a boom in reasoning, reshaping what's possible in AI. Yet, 
until now, information retrieval systems have lagged behind, lacking the reasoning capabilities needed to fully support 
this new paradigm. That gap has finally been bridged. 
 
Reason-ModernColBERT rises to this challenge thanks to LightOn's long-standing commitment to late-interaction 
architectures. Its results have been made possible thanks to an entire ecosystem purposefully built over time, from 
pioneering the PyLate library, to developing ModernBERT, and setting new standards with GTE-ModernColBERT. This 
sustained investment enables us today to unlock game-changing performance in reasoning-driven retrieval with remarkable 
simplicity. The result: a new model for complex, reasoning-intensive search, powered by an infrastructure designed from 
the ground up for exactly this purpose. 
Breaking New Ground in Reasoning-Intensive Retrieval 
   -- Small Model, Big Results: Despite being just 150M parameters (over 45 times smaller than certain 
  competitors), Reason-ModernColBERT outperforms all models up to 7B parameters on BRIGHT, the gold-standard 
  benchmark for reasoning-intensive retrieval. It even outperforms ReasonIR-8B by over 2.5 NDCG@10 on Stack Exchange 
  queries. 
 
   -- Lightning-Fast and Streamlined Training: Built using LightOn's powerful PyLate library, 
  Reason-ModernColBERT has been trained in less than two hours with fewer than 100 lines of code. 
 
   -- Late-Interaction Advantage: Direct comparisons with dense single-vector models, trained on identical 
  data, highlight the consistent, striking lead enabled by late-interaction architecture. 
 
Unlocking the Next Frontier of Research 
Reason-ModernColBERT is built to drive advanced knowledge exploration, addressing cases in which questions are nuanced 
and relevance is often subtle or implicit. 
 
As agentic RAG, advanced document understanding, and domain-specific research become central to enterprise AI, 
LightOn's new model provides: 
 
   -- Enhanced retrieval for subtle, implicit, or reasoning-based queries 
   -- Drastically reduced inference latency relative to massive LLMs 
   -- Easy reproducibility and transparency via open-source release 
 
Reaffirming LightOn's Commitment to Open Research 
As with our previous models, LightOn is making Reason-ModernColBERT, its training code, and the relevant datasets 
publicly available. Anyone can freely access, extend, and build upon it, leveraging PyLate to drive the next generation 
of multi-vector retrieval innovation. 
Get Started Today 
Reason-ModernColBERT is available now for use and experimentation on Hugging Face through PyLate, with comprehensive 
documentation and code for easy fine-tuning and deployment. Whether for knowledge management teams, AI developers, or 
scientific researchers, 
 
Reason-ModernColBERT opens new horizons in the age of Deep Research. 
?? Try Reason-ModernColBERT on Hugging Face 
?? PyLate Documentation 
 
About LightOn 
Founded in 2016 in Paris and the first European generative AI company listed on Euronext Growth, LightOn is a 
pioneering player in the field of sovereign GenAI. Its Paradigm platform enables organizations to deploy large-scale AI 
while ensuring the confidentiality of their data. LightOn's technology ensures essential strategic independence by 
offering tailored solutions. This technological mastery is accompanied by the ability to process large volumes of data 
for industrial uses, with applications in various sectors such as finance, industry, health, defense, and public 
services. 
LightOn is listed on Euronext Growth® Paris (ISIN: FR0013230950, ticker: ALTAI-FR). The company qualifies for PEA and 
PEA PME investment plans and is recognized as an "Innovative Company" by Bpifrance. To learn more: https:// 
www.lighton.ai 
 
 
Contacts 
                   SEITOSEI  --ACTIFIN 
LIGHTON                Investor Relations 
[e-mail]           Benjamin LEHARI 
                   [e-mail] 
KALAMARI 
                   SEITOSEI  --ACTIFIN 
Media Relations            Financial Media Relations 
Camille Bernisson - [phone] Jennifer JULLIA - [phone] 
Maroua Derdega - [phone]  [e-mail] 
[e-mail] 

-----------------------------------------------------------------------------------------------------------------------

Regulatory filing PDF file File: Reason-ModernColBERT PR

=---------------------------------------------------- 
Language:    English 
Company:     LIGHTON 
         2 rue de la Bourse 
         75002 Paris 
         France 
E-mail:     [e-mail] 
Internet:    www.lighton.ai 
ISIN:      FR0013230950 
Euronext Ticker: 
AMF Category:  Inside information / Other releases 
EQS News ID:   2143974 
 
End of Announcement EQS News Service 
=------------------------------------------------------------------------------------ 

2143974 22-May-2025 CET/CEST

Image link: https://eqs-cockpit.com/cgi-bin/fncls.ssp?fn=show_t_gif&application_id=2143974&application_name=news&site_id=dow_jones%7e%7e%7ef1066a31-ca00-4e1a-b0a4-374bd7d0face

(END) Dow Jones Newswires

May 22, 2025 12:15 ET (16:15 GMT)