papers

Publications (11)

cs.LG2025

Benchmarking Predictive Coding Networks -- Made Simple

Luca Pinchetti, Chang Qi, Oleh Lokshyn +9

In this work, we tackle the problems of efficiency and scalability for predictive coding networks (PCNs) in machine learning. To do so, we propose a library, called PCX, that focus…

cs.HC2024

Fool Me Once? Contrasting Textual and Visual Explanations in a Clinical Decision-Support Setting

Maxime Kayser, Bayar Menzat, Cornelius Emde +7

The growing capabilities of AI models are leading to their wider use, including in safety-critical domains. Explainable AI (XAI) aims to make these models safer to use by making th…

cs.CL2026

MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations

Elena Sofia Ruzzetti, Cornelius Emde, Sangdoo Yun +2

LLM agents are increasingly deployed in multi-party environments, handling sensitive personal data on behalf of individual users, for instance in group chats. When such an agent di…

cs.LG2025

Towards Certification of Uncertainty Calibration under Adversarial Attacks

Cornelius Emde, Francesco Pinto, Thomas Lukasiewicz +2

Since neural classifiers are known to be sensitive to adversarial perturbations that alter their accuracy, \textit{certification methods} have been developed to provide provable gu…

cs.CL2025

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou +39

Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstrac…

cs.CV2021

e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks

Maxime Kayser, Oana-Maria Camburu, Leonard Salewski +4

Recently, there has been an increasing number of efforts to introduce models capable of generating natural language explanations (NLEs) for their predictions on vision-language (VL…

cs.CL2025

Shh, don't say that! Domain Certification in LLMs

Cornelius Emde, Alasdair Paren, Preetham Arvind +6

Large language models (LLMs) are often deployed to perform constrained tasks, with narrow domains. For example, customer support bots can be built on top of LLMs, relying on their…

cs.CV2022

Explaining Chest X-ray Pathologies in Natural Language

Maxime Kayser, Cornelius Emde, Oana-Maria Camburu +3

Most deep learning algorithms lack explanations for their predictions, which limits their deployment in clinical practice. Approaches to improve explainability, especially in medic…

cs.NE2024

A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks

Tommaso Salvatori, Yuhang Song, Yordan Yordanov +6

Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience. Training such models, however, is quite inefficient and unstabl…

cs.CL2026

Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models

Anmol Goel, Cornelius Emde, Sangdoo Yun +2

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can de…

cs.AI2026

MASEval: Extending Multi-Agent Evaluation from Models to Systems

Cornelius Emde, Alexander Rubinstein, Anmol Goel +4

The rapid adoption of LLM-based agentic systems has produced a rich ecosystem of frameworks (smolagents, LangGraph, AutoGen, CAMEL, LlamaIndex, i.a.). Yet existing benchmarks are m…