14 citations · 16 across the 18 of their papers we have counts for
18 papers
Breaking the Likelihood Trap: Variance-Calibrated Modulation for Large Language Model Decoding
Yuanhao Ding, Meimingwei Li, Esteban Garces Arias +3
In open-ended generation, LLMs frequently fall into the "likelihood trap", characterized by repetitive degeneration and vocabulary dullness, resulting in a discrepancy between mach…
Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
Meimingwei Li, Yuanhao Ding, Esteban Garces Arias +1
Recent work has identified a counterintuitive phenomenon termed "Hyperfitting", where fine-tuning Large Language Models (LLMs) to near-zero training loss on small datasets surprisi…
Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration
Chongsheng Zhang, Hao Wang, Zelong Yu +7
Imbalanced data are commonly present in real-world applications. While data synthesis can effectively mitigate data scarcity for rare classes, and LLMs have revolutionized text gen…
Min- Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
Yuanhao Ding, Meimingwei Li, Esteban Garces Arias +3
The quality of text generated by large language models depends critically on the decoding sampling strategy. While mainstream methods such as Top-, Top-, and Min- achieve…
The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
Esteban Garces Arias, Nurzhan Sapargali, Christian Heumann +1
Why does machine-generated text remain detectable? We investigate a mechanistic explanation at the decoding stage: standard strategies such as top- and nucleus sampling restrict…
The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models
Esteban Garces Arias, Julian Rodemann, Christian Heumann
Understanding uncertainty in large language models remains a fundamental challenge, particularly in creative tasks where multiple valid outputs exist. We present a geometric framew…
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation
Yuanhao Ding, Esteban Garces Arias, Meimingwei Li +6
Open-ended text generation faces a critical challenge: balancing coherence with diversity in LLM outputs. While contrastive search-based decoding strategies have emerged to address…
Are All Genders Equal in the Eyes of Algorithms? -- Analysing Search and Retrieval Algorithms for Algorithmic Gender Fairness
Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher +3
Algorithmic systems such as search engines and information retrieval platforms significantly influence academic visibility and the dissemination of knowledge. Despite assumptions o…
Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corpora
Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher +2
Language corpora are the foundation of most natural language processing research, yet they often reproduce structural inequalities. One such inequality is gender discrimination in…
Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages
Matthias Schöffel, Esteban Garces Arias, Marinus Wiedner +4
Part-of-speech (POS) tagging remains a foundational component in natural language processing pipelines, particularly critical for historical text analysis at the intersection of co…
taz2024full: Analysing German Newspapers for Gender Bias and Discrimination across Decades
Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher +2
Open-access corpora are essential for advancing natural language processing (NLP) and computational social science (CSS). However, large-scale resources for German remain limited,…
Explainable Coarse-to-Fine Ancient Manuscript Duplicates Discovery
Chongsheng Zhang, Shuwen Wu, Yingqi Chen +5
Ancient manuscripts are the primary source of ancient linguistic corpora. However, many ancient manuscripts exhibit duplications due to unintentional repeated publication or delibe…
Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan
Matthias Schöffel, Marinus Wiedner, Esteban Garces Arias +3
Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing, yet their effectiveness in handling historical languages remains largely unex…
Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework
Esteban Garces Arias, Hannah Blocher, Julian Rodemann +3
Open-ended text generation has become a prominent task in natural language processing due to the rise of powerful (large) language models. However, evaluating the quality of these…
Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation
Esteban Garces Arias, Meimingwei Li, Christian Heumann +1
Decoding strategies for generative large language models (LLMs) are a critical but often underexplored aspect of text generation tasks. Guided by specific hyperparameters, these st…
Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation
Luis Mayer, Christian Heumann, Matthias Aßenmacher
In recent years, large language models (LLMs) have emerged as powerful tools with potential applications in various fields, including software engineering. Within the scope of this…
Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation
Esteban Garces Arias, Julian Rodemann, Meimingwei Li +2
Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, s…
How Prevalent is Gender Bias in ChatGPT? -- Exploring German and English ChatGPT Responses
Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher +2
With the introduction of ChatGPT, OpenAI made large language models (LLM) accessible to users with limited IT expertise. However, users with no background in natural language proce…