arXiv subjects

Zeno Jonke

Publications and source records attributed to Zeno Jonke.

5 recordsLinked to original sources

arXiv2026

Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition

As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and adapting them to other languages is hindered by the scarcity and cost of human-annotated judgments in most languages. We introduce a decomposition-based evaluation framework built around a Universal Criteria Set (UCS). UCS consists of a shared, language-agnostic set of evaluation dimensions, producing an interpretable intermediate representation that supports cross-lingual transfer with minimal supervision. Experiments on multiple faithfulness tasks across languages and model backbones demonstrate consistent improvements over strong baselines without requiring target-language annotations.

cs.CL↗

arXiv2025

Multilingual Self-Taught Faithfulness Evaluators

The growing use of large language models (LLMs) has increased the need for automatic evaluation systems, particularly to address the challenge of information hallucination. Although existing faithfulness evaluation approaches have shown promise, they are predominantly English-focused and often require expensive human-labeled training data for fine-tuning specialized models. As LLMs see increased adoption in multilingual contexts, there is a need for accurate faithfulness evaluators that can operate across languages without extensive labeled data. This paper presents Self-Taught Evaluators for Multilingual Faithfulness, a framework that learns exclusively from synthetic multilingual summarization data while leveraging cross-lingual transfer learning. Through experiments comparing language-specific and mixed-language fine-tuning approaches, we demonstrate a consistent relationship between an LLM's general language capabilities and its performance in language-specific evaluation tasks. Our framework shows improvements over existing baselines, including state-of-the-art English evaluators and machine translation-based approaches.

cs.CL↗

arXiv2017

A probabilistic model for learning in cortical microcircuit motifs with data-based divisive inhibition

Previous theoretical studies on the interaction of excitatory and inhibitory neurons proposed to model this cortical microcircuit motif as a so-called Winner-Take-All (WTA) circuit. A recent modeling study however found that the WTA model is not adequate for data-based softer forms of divisive inhibition as found in a microcircuit motif in cortical layer 2/3. We investigate here through theoretical analysis the role of such softer divisive inhibition for the emergence of computational operations and neural codes under spike-timing dependent plasticity (STDP). We show that in contrast to WTA models - where the network activity has been interpreted as probabilistic inference in a generative mixture distribution - this network dynamics approximates inference in a noisy-OR-like generative model that explains the network input based on multiple hidden causes. Furthermore, we show that STDP optimizes the parameters of this model by approximating online the expectation maximization (EM) algorithm. This theoretical analysis corroborates a preceding modelling study which suggested that the learning dynamics of this layer 2/3 microcircuit motif extracts a specific modular representation of the input and thus performs blind source separation on the input statistics.

q-bio.NC↗

arXiv2017

Feedback inhibition shapes emergent computational properties of cortical microcircuit motifs

Cortical microcircuits are very complex networks, but they are composed of a relatively small number of stereotypical motifs. Hence one strategy for throwing light on the computational function of cortical microcircuits is to analyze emergent computational properties of these stereotypical microcircuit motifs. We are addressing here the question how spike-timing dependent plasticity (STDP) shapes the computational properties of one motif that has frequently been studied experimentally: interconnected populations of pyramidal cells and parvalbumin-positive inhibitory cells in layer 2/3. Experimental studies suggest that these inhibitory neurons exert some form of divisive inhibition on the pyramidal cells. We show that this data-based form of feedback inhibition, which is softer than that of winner-take-all models that are commonly considered in theoretical analyses, contributes to the emergence of an important computational function through STDP: The capability to disentangle superimposed firing patterns in upstream networks, and to represent their information content through a sparse assembly code.

q-bio.NC↗

arXiv2014

A theoretical basis for efficient computations with noisy spiking neurons

Network of neurons in the brain apply - unlike processors in our current generation of computer hardware - an event-based processing strategy, where short pulses (spikes) are emitted sparsely by neurons to signal the occurrence of an event at a particular point in time. Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes. However it turned out to be surprisingly difficult to design networks of spiking neurons that are able to carry out demanding computations. We present here a new theoretical framework for organizing computations of networks of spiking neurons. In particular, we show that a suitable design enables them to solve hard constraint satisfaction problems from the domains of planning - optimization and verification - logical inference. The underlying design principles employ noise as a computational resource. Nevertheless the timing of spikes (rather than just spike rates) plays an essential role in the resulting computations. Furthermore, one can demonstrate for the Traveling Salesman Problem a surprising computational advantage of networks of spiking neurons compared with traditional artificial neural networks and Gibbs sampling. The identification of such advantage has been a well-known open problem.

cs.NE↗