Loris D'Antoni — accepted AI-conference papers

2025

Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective

Emmanuel Anaya Gonzalez, Sairam Vaidya, Kanghee Park, Ruyi Ji, Taylor Berg-Kirkpatrick, Loris D'Antoni

NeurIPS 2025poster

Constrained decoding enables Language Models (LMs) to produce samples that provably satisfy hard constraints. However, existing constrained-decoding approaches often distort the underlying model distribution, a limitation that is especially problematic in applications like program fuzzing, where one…

Cited by 0 Source ↗Scholar ↗

2025

Flexible and Efficient Grammar-Constrained Decoding

Kanghee Park, Timothy Zhou, Loris D'Antoni

ICML 2025poster

Large Language Models (LLMs) are often asked to generate structured outputs that obey precise syntactic rules, such as code snippets or formatted data. Grammar-constrained decoding (GCD) can guarantee that LLM outputs matches such rules by masking out tokens that will provably lead to outputs that d…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

Grammar-Aligned Decoding

Kanghee Park, Jiayu Wang, Taylor Berg-Kirkpatrick, Nadia Polikarpova, Loris D'Antoni

NeurIPS 2024poster

Large Language Models (LLMs) struggle with reliably generating highly structured outputs, such as program code, mathematical formulas, or well-formed markup. Constrained decoding approaches mitigate this problem by greedily restricting what tokens an LLM can output at each step to guarantee that the…

Cited by 10 Source ↗PDF ↗Scholar ↗

2022

BagFlip: A Certified Defense Against Data Poisoning

Yuhao Zhang, Aws Albarghouthi, Loris D'Antoni

NeurIPS 2022accept

Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but not the test inputs, while in a backdoor attack the attacke…

Cited by 27 Source ↗PDF ↗code ↗Scholar ↗

2021

Certifying Robustness to Programmable Data Bias in Decision Trees

Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni

NeurIPS 2021poster

Datasets can be biased due to societal inequities, human biases, under-representation of minorities, etc. Our goal is to certify that models produced by a learning algorithm are pointwise-robust to dataset biases. This is a challenging problem: it entails learning models for a large, or even infinit…

Cited by 21 Source ↗PDF ↗Scholar ↗