activity
20242026
collaborators

6 papers

cs.CR2026

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

Yannick Assogba, Jacopo Cortellazzi, Javier Abad +3

Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-based defense that identifies jailbrea…

stat.ML2026

Doubly robust identification of treatment effects from multiple environments

Piersilvio De Bartolomeis, Julia Kostin, Javier Abad +2

Practical and ethical constraints often require the use of observational data for causal inference, particularly in medicine and social sciences. Yet, observational datasets are pr…

stat.ME2026

Detecting critical treatment effect bias in small subgroups

Piersilvio De Bartolomeis, Javier Abad, Konstantin Donhauser +1

Randomized trials are considered the gold standard for making informed decisions in medicine, yet they often lack generalizability to the patient populations in clinical practice.…

stat.ML2026

Hidden yet quantifiable: A lower bound for confounding strength using randomized trials

Piersilvio De Bartolomeis, Javier Abad, Konstantin Donhauser +1

In the era of fast-paced precision medicine, observational studies play a major role in properly evaluating new treatments in clinical practice. Yet, unobserved confounding can sig…

cs.LG2025

Efficient Randomized Experiments Using Foundation Models

Piersilvio De Bartolomeis, Javier Abad, Guanbo Wang +4

Randomized experiments are the preferred approach for evaluating the effects of interventions, but they are costly and often yield estimates with substantial uncertainty. On the ot…

cs.LG2024

Copyright-Protected Language Generation via Adaptive Model Fusion

Javier Abad, Konstantin Donhauser, Francesco Pinto +1

The risk of language models reproducing copyrighted material from their training data has led to the development of various protective measures. Among these, inference-time strateg…