Papers by Esteban Garces Arias

7 papers
Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation (2025.coling-main)

Copied to clipboard

Challenge: Generative large language models generate a high-dimensional probability distribution over all tokens in their vocabulary.
Approach: They conduct extensive sensitivity analyses to determine how hyperparameter choices shape the outputs of generative large language models.
Outcome: The proposed methods influence the distribution of diversity and coherence metrics in human-written text, but the optimal configurations vary across models and tasks.
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.
Digitizing Nepal’s Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts (2026.acl-long)

Copied to clipboard

Challenge: Using a line-level transcription approach, we explore encoder-decoder architectures and data-centric techniques to improve recognition accuracy for Old Nepali manuscripts.
Approach: They propose a line-level transcription approach and explore encoder-decoder architectures and data-centric techniques to improve recognition accuracy.
Outcome: The proposed model achieves a 4.9% error rate and is highly reliable.
Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to synthesis of relational/structured tabular data lack effective feedback mechanism to optimize quality of generated data.
Approach: They propose a relational data generator with dynamic guidance framework that uses chain-of-thought steps to generate tabular data for enhancing downstream imbalanced classification performance.
Outcome: The proposed framework outperforms existing approaches in both data fidelity and downstream imbalanced classification performance on real and synthetic datasets.
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.
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.

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