Sebastian Hofstätter
I'm an engineer and researcher at Cohere teaching LLMs about relevance.
I received my PhD from TU Vienna supervised by Prof. Allan
Hanbury. During my PhD I worked in the field of Information Retrieval on efficient & interpretable neural re-ranking and effective
dense retrieval models.
I studied and tried to optimize the cost-effectiveness tradeoff from multiple angles, so that everyone can deploy those techniques.
In addition, I created an award-winning master-level course to teach neural advances in IR – all of which is open-source
🎉
Find me on Twitter, GitHub, and HuggingFace!
Research
During my PhD internship at Google Research I worked on efficient & effective retrieval augmented generation.
Retrieval Augmented Generation
2023arXiv
SIGIR
(Full)
FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation
2022KRLM@ICML
(Workshop)
Multi-Task Retrieval-Augmented Text Generation with Relevance Sampling
During my PhD I worked on the topic of "Optimizing the Cost-Effectiveness Tradeoff in Neural Ranking" from multiple angles, split into two main parts:
Neural Retrieval & Knowledge Distillation
Dense retrieval (using a nearest neighbor vector search) gained quick popularity as a promising future of search – I am focused on utilizing knowledge distillation from stronger, but slower teacher models to improve the dense retrieval quality.
(Full) Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systems
2022CIKM
(Full) Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction
2021SIGIR
(Full) Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling
2020arXiv
(Full) Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation
2019ECIR
(Short) Enriching Word Embeddings for Patent Retrieval with Global Context
⭐ Won best systems short paper award
Efficient & Interpretable Neural Re-Ranking
Neural re-ranking models always add time to the query latency, therefore I focus on improving the efficiency for short and long text neural re-ranking models.
(Short) Establishing Strong Baselines for TripClick Health Retrieval
2021TREC TU Wien at TREC DL and Podcast 2021: Simple Compression for Dense Retrieval
2021SIGIR
(Full) Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking
2021ECIR
(Full) Mitigating the Position Bias of Transformer Models in Passage Re-Ranking
2020TREC Evaluating Transformer-Kernel Models at TREC Deep Learning 2020
2020SIGIR
(Short) Local Self-Attention over Long Text for Efficient Document Retrieval
2020CIKM
(Short) Learning to Re-Rank with Contextualized Stopwords
2020CIKM
(Resource) Fine-Grained Relevance Annotations for Multi-Task Document Ranking and Question Answering
2020ECAI
(Full) Interpretable & Time-Budget-Constrained Contextualization for Re-Ranking
2020ECIR
(Demo) Neural-IR-Explorer: A Content-Focused Tool to Explore Neural Re-Ranking Results
2019TREC TU Wien @ TREC Deep Learning ’19 – Simple Contextualization for Re-ranking
2019SIGIR
(Short) On the Effect of Low-Frequency Terms on Neural-IR Models
2019OSIRRC
(Workshop) Let’s measure runtime!
For all my publications (including collaborations) visit Google or Semantic Scholar.
Teaching
All my materials are available open-source on GitHub. For a detailed description of our workflow for remote teaching see:
(Full) A Time-Optimized Content Creation Workflow for Remote Teaching
Advanced Information Retrieval (Summer 2022, 2021, 2020, 2019)
Full responsibility and main lecturer for the master-level course with > 100 students on neural methods for IR. Including designing, conducting, and grading of lectures, exercises, and exams.
A playlist of all lecture recordings from 2021 is available on Youtube.
(10 lectures total) Exercise: Implement neural re-ranking models in PyTorch
🏆 Won Best Distance Learning Lecture & Best Teacher Award 2021 @ TU Wien
Introduction to Information Retrieval (Winter 2019, 2018)
Experience & Education
2022Research Internship - Google Research (3.5 months) 2021Visiting Scholar - UMass Amherst (2 months) 2018 - 2022PhD - Computer Science - TU Wien 2016 - 2018Master's - Software Engineering - TU Wien 2012 - 2016Bachelor's - Computer Science and Economics - TU Wien