5 papers
Concept Tokens: Learning Behavioral Embeddings Through Concept Definitions
Ignacio Sastre, Aiala Rosá
We propose Concept Tokens, a lightweight method that adds a new special token to a pretrained LLM and learns only its embedding from multiple natural language definitions of a targ…
On the Use of Large Language Models for Qualitative Synthesis
Sebastián Pizard, Ramiro Moreira, Federico Galiano +2
Large language models (LLMs) show promise for supporting systematic reviews (SR), even complex tasks such as qualitative synthesis (QS). However, applying them to a stage that is u…
Memory Tokens: Large Language Models Can Generate Reversible Sentence Embeddings
Ignacio Sastre, Aiala Rosá
In this work, we observe an interesting phenomenon: it is possible to generate reversible sentence embeddings that allow an LLM to reconstruct the original text exactly, without mo…
RETUYT-INCO at BEA 2025 Shared Task: How Far Can Lightweight Models Go in AI-powered Tutor Evaluation?
Santiago Góngora, Ignacio Sastre, Santiago Robaina +3
In this paper, we present the RETUYT-INCO participation at the BEA 2025 shared task. Our participation was characterized by the decision of using relatively small models, with fewe…
A Platform for Generating Educational Activities to Teach English as a Second Language
Aiala Rosá, Santiago Góngora, Juan Pablo Filevich +4
We present a platform for the generation of educational activities oriented to teaching English as a foreign language. The different activities -- games and language practice exerc…