Internship: Retrieval Augmented Generation
at
NAVER LABS Europe
Description
We're looking for students interested in improving retrieval augmented generation (RAG) in multilingual or multi-domain scenarios.
Based on a simple idea of augmenting user requests with relevant passages retrieved from the Internet or a given datastore, RAG has recently emerged as a promising solution to improve LLM factuality and grounded attribution. Despite high attention this research topic has received in recent years, the vast majority of work only focusses on Wikipedia-based English settings in their experiments, trained models or collected datasets. At the same time, initial efforts were made to evaluate or extend RAG to multi-domain [1, 2] or multilingual [3-6] settings.
The topic of this internship will be related to continuing to improve advanced RAG pipelines so that they better support queries and contexts in non-English or from various domains.
Internship supervisors: Nadezhda Chirkova, Thibault Formal, Vassilina Nikoulina
The intern will collaborate with a team of researchers with background in RAG [5-6], natural language generation [7-9] and information retrieval [10-12].
Required skills
- PhD or final year MSc student in NLP-related domains
- Solid deep learning and NLP background
- Experience with Pytorch toolkit
References
1: RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation. Dongyu Ru et al., NeurIPS 2024
2: RAFT: Adapting Language Model to Domain Specific RAG. Tianjun Zhang et al., COLM 2024
3: MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems. Nandan Thakur et al., 2024
4: Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation. Suhang Wu et al., 2024
5: BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. David Rau, Hervé Déjean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, Vassilina Nikoulina, Stéphane Clinchant. Findings of EMNLP 2024
6: Retrieval-augmented generation in multilingual settings. Nadezhda Chirkova, David Rau, Hervé Déjean, Thibault Formal, Stéphane Clinchant, Vassilina Nikoulina. Knowledgeable LLMs workshop @ ACL 2024
7: Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks. Nadezhda Chirkova and Vasilina Nikoulina, NAACL 2024
8: Zero-shot cross-lingual transfer in instruction tuning of large language models. Nadezhda Chirkova and Vasilina Nikoulina, INLG 2024
9: BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting. Zheng Xin Yong et al., ACL 2023.
10: SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant, SIGIR 2021
11: MS-Shift: An Analysis of MS MARCO Distribution Shifts on Neural Retrieval. Simon Lupart, Thibault Formal, Stéphane Clinchant, ECIR 2023
12: Splate: Sparse late interaction retrieval. Thibault Formal, Stéphane Clinchant, Hervé Déjean, Carlos Lassance. SIGIR 2024
Application instructions
Please note that applicants must be registered students at a university or other academic institution and that this establishment will need to sign an 'Internship Convention' with NAVER LABS Europe before the student is accepted.
You can apply for this position online. Don't forget to upload your CV and cover letter before you submit. Incomplete applications will not be accepted.
About NAVER LABS
NAVER is the #1 Internet portal in Korea with activities that span a wide range of businesses including search, commerce, content, financial and cloud platforms.
NAVER LABS, co-located in Korea and France, is the organization dedicated to preparing NAVER’s future. NAVER LABS Europe is located in a spectacular setting in Grenoble, in the heart of the French Alps. Scientists at NAVER LABS Europe are empowered to pursue long-term research problems that, if successful, can have significant impact and transform NAVER. We take our ideas as far as research can to create the best technology of its kind. Active participation in the academic community and collaborations with world-class public research groups are, among others, important tools to achieve these goals. Teamwork, focus and persistence are important values for us.
NAVER LABS Europe is an equal opportunity employer.
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
VISION
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.