Alex Laitenberger

AI / NLP Research — Language Model Systems, Retrieval, Evaluation

I am an NLP researcher focused on improving the reliability and factual accuracy of language model systems, particularly through retrieval and evaluation. My recent work, conducted in collaboration with Christopher D. Manning and Nelson F. Liu, was published at EMNLP 2025. It shows that strong, well-designed RAG baselines can match or outperform more complex multi-step pipelines in long-context QA, highlighting the importance of retrieval recall. I am particularly interested in how models access and reason over information, including retrieval-augmented generation, evaluation design, and agentic systems.

I am currently open to research roles in industry and academia, with a focus on language model development, retrieval, evaluation, and system-level approaches to improving factuality and reliability.

[LinkedIn] [Google Scholar] [GitHub] [CV]

---

Publications

Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models
Alex Laitenberger, Christopher D. Manning, Nelson F. Liu.
EMNLP 2025 (Main Conference), Suzhou, China, 2025.
[Code] [Poster]

Expanding Horizons in RAG: Exploring and Extending the Limits of RAPTOR
Alex Laitenberger.
Research Project (Stanford CS224N), 2024.
[Poster]

Concept for Discovering Relevant Information through the Automated Analysis of News Articles
Alex Laitenberger.
Bachelor’s Thesis, 2011.

Evaluating Product-Market Fit for a Consumer-Oriented App Startup
Alex Laitenberger.
Master’s Thesis, 2018