Skip to content

Author

Nils Feldhus

5 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Conference Open access Nov 2026

Training-Free Character-Length Control in Summarization with Diffusion Language Models

This work proposes DELTA (Diffusion Expected Length Targeting Algorithm), a training-free inference-time method for masked diffusion LMs that estimates expected character length at each denoising step and dynamically inserts or removes masked positions to steer toward a target length.

Steffen Castle, Nils Feldhus, Christopher Ebert et al. · 0 citations
#artificial intelligence Open access Oct 2026

SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI

Conversational explainable AI (ConvXAI) agents often use GUS-style architectures with separate modules for intent recognition, dialogue management, and template-based response generation. While faithful to the underlying XAI methods, these pipelines are hard to adapt and often struggle with context-dependent follow-up...

Van Bach Nguyen, Qianli Wang, Nils Feldhus et al. · 0 citations

From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness

Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through input--output behavior or input attributions, leaving internal computation largely underexplored. We instead cast faithfulness as internal concept grounding: Does a large lan...

Qianli Wang, Yi-Long Wang, Dennis Wei et al. · 1 citation
#machine learning Preprint May 2026

Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge

By structurally decoupling abstract judging from output formatting, this work provides a mechanistic account of format-induced inconsistency on the open-weight models the authors study and implies that benchmark comparisons of judge reliability across formats partly measure the fragile formatting stage, and can underst...

Nils Feldhus, Tanja Baeumel, Elena Golimblevskaia et al. · 1 citation
#machine learning Preprint Sep 2026

Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations

This work qualitatively replicate and extend ConSim's ranking of explanation methods across the tested datasets, explanation families, and simulator LLMs, and identifies two limitations: when class names are meaningful, simulators can obtain high simulatability by solving the classification task directly, without relyi...

Antonin Poché, Fanny Jourdan, Nils Feldhus et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.