Papers by Matthias Aßenmacher

10 papers
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: GUARD is a self-adaptive decoding method that balances coherence with diversity in open-ended text generation.
Approach: They propose a self-adaptive decoding method that balances coherence and diversity . they combine global entropy estimates with local entropic deviations to integrate uncertainty .
Outcome: GUARD achieves a good balance between diversity and coherence while exhibiting significant improvements in generation speed.
Divergent Token Metrics: Measuring degradation to prune away LLM components – and optimize quantization (2024.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have reshaped natural language processing with impressive capabilities, but their ever-increasing size has raised concerns about their effective deployment and the need for LLM compression.
Approach: This study introduces the Divergent Token Metrics (DTMs) that measure token divergences that allow deeper insights into the subtleties of model compression.
Outcome: The proposed measures can identify outliers and improve performance in the sparseness of the LLMs.
taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades (2025.findings-acl)

Copied to clipboard

Challenge: a large corpus of German newspaper articles is available for free in other languages, such as English.
Approach: They propose to use taz2024full to analyse gender representation across four decades of reporting.
Outcome: The proposed corpus supports a wide range of applications from diachronic language analysis to critical media studies.
Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have generated significant interest in their potential for synthetic data generation across various domains.
Approach: They use open-ended survey data from the German Longitudinal Election Studies to prompt different LLMs to generate synthetic public opinions reflective of German subpopulations by incorporating demographic features into the persona prompts.
Outcome: The LLM performs better for supporters of left-leaning parties like The Greens and The Left compared to other parties, and matches the least with the right-party AfD.
Can Calibration of Positional Encodings Enhance Long Context Utilization? (2026.findings-eacl)

Copied to clipboard

Challenge: Large language models suffer from positional biases that reduce effective utilization of long contexts.
Approach: They propose a training-free framework for calibrating Positional Encodings at inference time.
Outcome: The proposed framework improves on needle-in-a-haystack and cross-chunk reasoning benchmarks and provides a lightweight method for improving long-context utilization.
Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to decode text to the most probable sequence have been proposed to address these challenges by improving coherence, diversity, and resemblance to human-generated text.
Approach: They propose a novel decoding strategy that extends contrastive search by incorporating an adaptive degeneration penalty informed by the model’s estimated uncertainty at each generation step.
Outcome: The proposed approach improves creativity and coherence while maintaining coherency across model architectures, languages, and datasets.
Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for decoding large language models have extreme sensitivity to temperature parameter T.
Approach: They propose a dynamic truncation strategy that analyzes the local shape of the logit distribution to identify "semantic cliffs" they show that Min-k consistently improves text quality even under extreme temperature settings .
Outcome: The proposed method achieves strict temperature invariance and low sensitivity to hyperparameter choices.
promptolution: A Unified, Modular Framework for Prompt Optimization (2026.eacl-demo)

Copied to clipboard

Challenge: Existing implementations of prompt optimization are tied to unmaintained, isolated codebases or require invasive integration into application frameworks.
Approach: They propose a unified, modular open-source framework that integrates multiple contemporary discrete prompt optimizers within a single extensible system for both practitioners and researchers.
Outcome: The proposed framework integrates multiple discrete prompt optimizers, supports systematic and reproducible benchmarking, and returns framework-agnostic prompt strings, enabling seamless integration into existing LLM pipelines while remaining agnosite to the underlying model implementation.
Automatic Transcription of Handwritten Old Occitan Language (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to handwritten text recognition have shown promising results, but low-resource languages often lack resources.
Approach: They propose an HTR approach that leverages the Transformer architecture for recognizing handwritten Old Occitan language.
Outcome: The proposed approach surpasses state-of-the-art models for Old Occitan HTR, including open-source Transformer-based models and commercial applications like Google Cloud Vision.
Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News (2020.coling-main)

Copied to clipboard

Challenge: Using unsupervised representation learning, automated Fake News detection is a challenge for researchers.
Approach: They examine pre-trained language models with respect to their performance on two Fake News related data sets.
Outcome: The proposed models outperform the autoregression-based models on two Fake News related data sets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations