Controllable Language Models

We study the techniques for making large language models more controllable and reliable as part of larger systems. Our work focuses on structured and constrained generation, model routing, and hallucination prevention.

Publications

2025

Constrained Decoding of Diffusion LLMs with Context-Free Grammars

Niels Mündler, Jasper Dekoninck, Martin Vechev

arXiv 2025

Website
Paper
Code

A Unified Approach to Routing and Cascading for LLMs

Jasper Dekoninck, Maximilian Baader, Martin Vechev

ICML 2025

Paper
Code

Type-Constrained Code Generation with Language Models

Niels Mündler^†, Jingxuan He^†, Hao Wang, Koushik Sen, Dawn Song, Martin Vechev

PLDI 2025 † Co-leadership

Slides
Talk
Paper
Code

2024

Prompt Sketching for Large Language Models

Luca Beurer-Kellner, Mark Niklas Müller, Marc Fischer, Martin Vechev

ICML 2024

Paper
Code

Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation

Luca Beurer-Kellner, Marc Fischer, Martin Vechev

ICML 2024

Paper
Code

Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation

Niels Mündler, Jingxuan He, Slobodan Jenko, Martin Vechev

ICLR 2024

Website
Paper
Code

Controlled Text Generation via Language Model Arithmetic

Jasper Dekoninck, Marc Fischer, Luca Beurer-Kellner, Martin Vechev

ICLR 2024 Spotlight

Paper
Code

2023

LMQL Chat: Scripted Chatbot Development

Luca Beurer-Kellner*, Marc Fischer*, Martin Vechev

Neural Conversational AI Workshop, TEACH -- ICML 2023 * Equal contribution

Paper
Code

Large Language Models are Zero-Shot Multi-Tool Users

Luca Beurer-Kellner*, Marc Fischer*, Martin Vechev

Knowlege and Logical Reasoning Workshop -- ICML 2023 * Equal contribution

Paper
Code

Prompting Is Programming: A Query Language for Large Language Models

Luca Beurer-Kellner, Marc Fischer, Martin Vechev

PLDI 2023

Paper
Code