activity
20162024
most citedGuiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation

3 citations · 10 across the 11 of their papers we have counts for

collaborators

11 papers

cs.LG2024

AlphaIntegrator: Transformer Action Search for Symbolic Integration Proofs

Mert Ünsal, Timon Gehr, Martin Vechev

We present the first correct-by-construction learning-based system for step-by-step mathematical integration. The key idea is to learn a policy, represented by a GPT transformer mo…

cs.LG2024

Mitigating Catastrophic Forgetting in Language Transfer via Model Merging

Anton Alexandrov, Veselin Raychev, Mark Niklas Müller +3

As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different…

cs.CR20243 cited

DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models

Berkay Berabi, Alexey Gronskiy, Veselin Raychev +3

The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semant…

cs.LG20243 cited

Evading Data Contamination Detection for Language Models is (too) Easy

Jasper Dekoninck, Mark Niklas Müller, Maximilian Baader +2

Large language models are widespread, with their performance on benchmarks frequently guiding user preferences for one model over another. However, the vast amount of data these mo…

cs.LG20243 cited

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

Luca Beurer-Kellner, Marc Fischer, Martin Vechev

To ensure that text generated by large language models (LLMs) is in an expected format, constrained decoding proposes to enforce strict formal language constraints during generatio…

cs.CV2024

Automated Classification of Model Errors on ImageNet

Momchil Peychev, Mark Niklas Müller, Marc Fischer +1

While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of…