Search Results for author: Javier Conde

Found 18 papers, 2 papers with code

Understanding the Impact of Artificial Intelligence in Academic Writing: Metadata to the Rescue

no code implementations23 Feb 2025 Javier Conde, Pedro Reviriego, Joaquín Salvachúa, Gonzalo Martínez, José Alberto Hernández, Fabrizio Lombardi

This column advocates for including artificial intelligence (AI)-specific metadata on those academic papers that are written with the help of AI in an attempt to analyze the use of such tools for disseminating research.

Speed and Conversational Large Language Models: Not All Is About Tokens per Second

no code implementations23 Feb 2025 Javier Conde, Miguel González, Pedro Reviriego, Zhen Gao, Shanshan Liu, Fabrizio Lombardi

The speed of open-weights large language models (LLMs) and its dependency on the task at hand, when run on GPUs, is studied to present a comparative analysis of the speed of the most popular open LLMs.

All

Can ChatGPT Learn to Count Letters?

no code implementations23 Feb 2025 Javier Conde, Gonzalo Martínez, Pedro Reviriego, Zhen Gao, Shanshan Liu, Fabrizio Lombardi

Large language models (LLMs) struggle on simple tasks such as counting the number of occurrences of a letter in a word.

Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident Even When They Are Wrong

no code implementations16 Jan 2025 Tairan Fu, Javier Conde, Gonzalo Martínez, María Grandury, Pedro Reviriego

In this paper, we study how the LLM confidence in its answer depends on whether the model has been asked to answer directly or to provide the reasoning before answering.

Multiple-choice

Enhanced FIWARE-Based Architecture for Cyberphysical Systems With Tiny Machine Learning and Machine Learning Operations: A Case Study on Urban Mobility Systems

no code implementations16 Nov 2024 Javier Conde, Andrés Munoz-Arcentales, Álvaro Alonso, Joaquín Salvachúa, Gabriel Huecas

This article extends a previous architecture based on FIWARE software components to implement the machine learning operations flow, enabling the management of the entire tinyML lifecycle in cyberphysical systems.

Edge-computing Management

Evaluation of real-time transcriptions using end-to-end ASR models

no code implementations9 Sep 2024 Carlos Arriaga, Alejandro Pozo, Javier Conde, Alvaro Alonso

For this reason, it is necessary to design and test different splitting algorithms to optimize the quality and delay of the resulting transcription.

Action Detection Activity Detection +3

Evaluating Large Language Models with Tests of Spanish as a Foreign Language: Pass or Fail?

no code implementations8 Sep 2024 Marina Mayor-Rocher, Nina Melero, Elena Merino-Gómez, María Grandury, Javier Conde, Pedro Reviriego

Large Language Models (LLMs) have been profusely evaluated on their ability to answer questions on many topics and their performance on different natural language understanding tasks.

Natural Language Understanding Reading Comprehension

Adaptive Resolution Inference (ARI): Energy-Efficient Machine Learning for Internet of Things

no code implementations26 Aug 2024 Ziheng Wang, Pedro Reviriego, Farzad Niknia, Javier Conde, Shanshan Liu, Fabrizio Lombardi

This enables most inferences to run with the reduced precision model and only a small fraction requires the full model, so significantly reducing computation and energy while not affecting model performance.

Quantization

How Stable is Stable Diffusion under Recursive InPainting (RIP)?

no code implementations27 Jun 2024 Javier Conde, Miguel González, Gonzalo Martínez, Fernando Moral, Elena Merino-Gómez, Pedro Reviriego

This process of recursively applying inpainting can lead to an image that is similar or completely different from the original one, depending on the fragments that are removed and the ability of the model to reconstruct them.

Text-to-Image Generation

Spanish and LLM Benchmarks: is MMLU Lost in Translation?

no code implementations28 May 2024 Irene Plaza, Nina Melero, Cristina del Pozo, Javier Conde, Pedro Reviriego, Marina Mayor-Rocher, María Grandury

Selected categories of the benchmark are translated into Spanish using Azure Translator and ChatGPT4 and run on ChatGPT4.

MMLU Translation

Concurrent Linguistic Error Detection (CLED) for Large Language Models

no code implementations25 Mar 2024 Jinhua Zhu, Javier Conde, Zhen Gao, Pedro Reviriego, Shanshan Liu, Fabrizio Lombardi

Since the proposed error detection mechanism only relies on the outputs of the model, then it can be used on LLMs in which there is no access to the internal nodes.

News Summarization valid

Open Conversational LLMs do not know most Spanish words

no code implementations21 Mar 2024 Javier Conde, Miguel González, Nina Melero, Raquel Ferrando, Gonzalo Martínez, Elena Merino-Gómez, José Alberto Hernández, Pedro Reviriego

The growing interest in Large Language Models (LLMs) and in particular in conversational models with which users can interact has led to the development of a large number of open-source chat LLMs.

Fairness

Beware of Words: Evaluating the Lexical Diversity of Conversational LLMs using ChatGPT as Case Study

no code implementations11 Feb 2024 Gonzalo Martínez, José Alberto Hernández, Javier Conde, Pedro Reviriego, Elena Merino

In this paper, we consider the evaluation of the lexical richness of the text generated by LLMs and how it depends on the model parameters.

Diversity Logical Reasoning

Establishing Vocabulary Tests as a Benchmark for Evaluating Large Language Models

1 code implementation23 Oct 2023 Gonzalo Martínez, Javier Conde, Elena Merino-Gómez, Beatriz Bermúdez-Margaretto, José Alberto Hernández, Pedro Reviriego, Marc Brysbaert

Vocabulary tests, once a cornerstone of language modeling evaluation, have been largely overlooked in the current landscape of Large Language Models (LLMs) like Llama, Mistral, and GPT.

Language Modeling Language Modelling

How many words does ChatGPT know? The answer is ChatWords

1 code implementation28 Sep 2023 Gonzalo Martínez, Javier Conde, Pedro Reviriego, Elena Merino-Gómez, José Alberto Hernández, Fabrizio Lombardi

The benefits of ChatWords are illustrated with two case studies: evaluating the knowledge that ChatGPT has of the Spanish lexicon (taken from the official dictionary of the "Real Academia Espa\~nola") and of the words that appear in the Quixote, the well-known novel written by Miguel de Cervantes.

Playing with Words: Comparing the Vocabulary and Lexical Richness of ChatGPT and Humans

no code implementations14 Aug 2023 Pedro Reviriego, Javier Conde, Elena Merino-Gómez, Gonzalo Martínez, José Alberto Hernández

Therefore, further research is needed to understand how the use of ChatGPT and more broadly generative AI tools will affect the vocabulary and lexical richness in different types of text and languages.

Cannot find the paper you are looking for? You can Submit a new open access paper.