publications

2025

1. NAACL 2025

   Bridging the Gap in Health Literacy: Harnessing the Power of Large Language Models to Generate Plain Language Summaries from Biomedical Texts

   Andrés Arias-Russi, Carolina Salazar-Lara, and Rubén Manrique

   In Proceedings of the Second Workshop on Patient-Oriented Language Processing (CL4Health), May 2025

   Abs

   Health literacy enables individuals to navigate healthcare systems and make informed decisions. Plain language summaries (PLS) can bridge comprehension gaps by simplifying complex biomedical texts, yet their manual creation is both time-consuming and challenging. This study advances the field by (1) constructing a novel corpus of paired technical and plain language texts from medical trial libraries, (2) developing machine learning classifiers to rapidly identify plain language features, and (3) establishing a multi-dimensional evaluation framework that integrates computational metrics with human expertise. We iteratively optimized prompts for diverse large language models (LLMs)—including GPT models, Gemini 1.5, DeepSeek-R1, and Llama-3.2—to generate PLS variants aligned with domain-specific guidelines. Our classifier achieved 97.5% accuracy in distinguishing plain from technical language, and the generated summaries demonstrated high semantic equivalence to expert-written versions.

2. EMNLP 2025

   A Multi-Agent Framework with Diagnostic Feedback for Iterative Plain Language Summary Generation from Cochrane Medical Abstracts

   Felipe Arias Russi, Carolina Salazar Lara, and Ruben Manrique

   In Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025), Nov 2025

   Abs

   Plain Language Summaries PLS improve health literacy and enable informed healthcare decisions but writing them requires domain expertise and is time-consuming. Automated methods often prioritize efficiency over comprehension and medical documents unique simplification requirements challenge generic solutions. We present a multi-agent system for generating PLS using Cochrane PLS as proof of concept. The system uses specialized agents for information extraction writing diagnosis and evaluation integrating a medical glossary and statistical analyzer to guide revisions. We evaluated three architectural configurations on 100 Cochrane abstracts using six LLMs both proprietary and open-source. Results reveal model-dependent trade-offs between factuality and readability with the multi-agent approach showing improvements for smaller models and providing operational advantages in control and interpretability.

3. EMNLP 2025

   Uniandes at TSAR 2025 Shared Task: Multi-Agent CEFR Text Simplification with Automated Quality Assessment and Iterative Refinement

   Felipe Arias Russi, Kevin Cohen Solano, and Ruben Manrique

   In Proceedings of the Fourth Workshop on Text Simplification, Accessibility and Readability (TSAR 2025), Nov 2025

   Abs

   We present an agent-based system for the TSAR 2025 Shared Task on Readability-Controlled Text Simplification, which requires simplifying English paragraphs from B2+ levels to target A2 or B1 levels while preserving meaning. Our approach employs specialized agents for keyword extraction, text generation, and evaluation, coordinated through an iterative refinement loop. The system integrates a CEFR vocabulary classifier, pretrained evaluation models, and few-shot learning from trial data. Through iterative feedback between the evaluator and writer agents, our system automatically refines outputs until they meet both readability and semantic preservation constraints. This architecture achieved 4th position among participating teams, showing the effectiveness of combining specialized LLMs with automated quality control strategies for text simplification.

4. ICCV 2025

   Guiding Multimodal Large Language Models with Blind and Low Vision Visual Questions for Proactive Visual Interpretations

   Ricardo Enrique Gonzalez Penuela, Felipe Arias-Russi, and Victor Capriles

   In CV4A11y Workshop at ICCV 2025, Aug 2025

   Abs arXiv

   Multimodal large language models (MLLMs) have been integrated into visual interpretation applications to support Blind and Low Vision (BLV) users because of their high accuracy and ability to provide rich, human-like interpretations. However, these applications often default to comprehensive, lengthy descriptions regardless of context. This leads to inefficient exchanges, as users must go through irrelevant details rather than receiving the specific information they are likely to seek. To deliver more contextually-relevant information, we developed a system that draws on historical BLV user questions. When given an image, our system identifies similar past visual contexts from the VizWiz-LF Dataset and uses the associated questions to guide the MLLM generate descriptions more relevant to BLV users. An evaluation with three human labelers who revised 92 context-aware and context-free descriptions showed that context-aware descriptions anticipated and answered users’ questions in 76.1% of cases (70 out of 92) and were preferred in 54.4% of comparisons (50 out of 92).

5. arXiv

   CARIS: A Context-Adaptable Robot Interface System for Personalized and Scalable Human-Robot Interaction

   Felipe Arias-Russi, Yuanchen Bai, and Angelique Taylor

   Aug 2025

   Abs

   The human-robot interaction (HRI) field has traditionally used Wizard-of-Oz (WoZ) controlled robots to explore navigation, conversational dynamics, human-in-the-loop interactions, and more to explore appropriate robot behaviors in everyday settings. However, existing WoZ tools are often limited to one context, making them less adaptable across different settings, users, and robotic platforms. To mitigate these issues, we introduce a Context-Adaptable Robot Interface System (CARIS) that combines advanced robotic capabilities such teleoperation, human perception, human-robot dialogue, and multimodal data recording. Through pilot studies, we demonstrate the potential of CARIS to WoZ control a robot in two contexts: 1) mental health companion and as a 2) tour guide. Furthermore, we identified areas of improvement for CARIS, including smoother integration between movement and communication, clearer functionality separation, recommended prompts, and one-click communication options to enhance the usability wizard control of CARIS. This project offers a publicly available, context-adaptable tool for the HRI community, enabling researchers to streamline data-driven approaches to intelligent robot behavior.