Papers by Barbara Di Eugenio
Veracity Bias and Beyond: Uncovering LLMs’ Hidden Beliefs in Problem-Solving Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been aligned to avoid harmful biases and stereotypes, but recent studies have revealed the superficial nature of this alignment. |
| Approach: | They propose to use large language models to avoid harmful biases and stereotypes by assigning personas to LLMs to observe decision discrepancies in social scenarios or asking them to associate specific attributes with social targets. |
| Outcome: | The proposed models attribute fewer correct solutions and more incorrect ones to African-American groups in math and coding, while Asian authorships are least preferred in writing evaluation. |
Modeling Low-Resource Health Coaching Dialogues via Neuro-Symbolic Goal Summarization and Text-Units-Text Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Health coaching is a patient-centered clinical practice that aims to help patients achieve personalized and lifestyle-related goals to enhance their health behaviors. |
| Approach: | They propose a neuro-symbolic goal summarizer to support health coaches in keeping track of the goals and a text-units-text dialogue generation model that converses with patients and helps them create and accomplish specific goals for physical activities. |
| Outcome: | The proposed model outperforms existing state-of-the-art models while eliminating the need for predefined schema and corresponding annotations. |
RoBERTa Low Resource Fine Tuning for Sentiment Analysis in Albanian (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in the education domain have provided new opportunities for solving interesting, but difficult problems. |
| Approach: | They propose to use EduSenti to fine-tune language models for assigning sentiment to reviews of educators' performance annotated for sentiment, emotion and educational topic. |
| Outcome: | The proposed model is compared with an Albanian masked language trained model from the last XLM-RoBERTa checkpoint and shows that it is a good fit for the proposed model. |
A New Public Corpus for Clinical Section Identification: MedSecId (2022.coling-1)
Copied to clipboard
| Challenge: | a study aims to segment sections of clinical medical domain documentation . section identification is a process by which sections are demarcated and labeled . |
| Approach: | They use a set of 2,002 fully annotated medical notes from the MIMIC-III to segment sections in clinical medical domain documentation. |
| Outcome: | The proposed model shows that medical concepts are related across sections using principal component analysis. |
Towards Generating Personalized Hospitalization Summaries (N18-4)
Copied to clipboard
Sabita Acharya, Barbara Di Eugenio, Andrew Boyd, Richard Cameron, Karen Dunn Lopez, Pamela Martyn-Nemeth, Carolyn Dickens, Amer Ardati
| Challenge: | 80% of the medical concepts that are considered important by both doctor and nurse are not included in the summaries provided to patients . |
| Approach: | They propose to combine information from discharge notes and nursing plan of care to generate personalized hospital-stay summaries for patients. |
| Outcome: | The summaries contain 80% of the medical concepts that are considered important by both doctor and nurses. |
CALAMR: Component ALignment for Abstract Meaning Representation (2024.lrec-main)
Copied to clipboard
| Challenge: | Abstract meaning representation (AMR) graphs represent semantic structure in a syntactic independent way. |
| Approach: | They propose a method for graph alignment that can support summarization and evaluation. |
| Outcome: | The proposed method produces graphs that explain what is summarized through their alignments, which can be used to train graph based summarization learners. |
Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing research has shown that large language models have difficulty discerning the veracity of their intrinsic answers. |
| Approach: | They propose a jailbreak attack method that generates an aligned language model for malicious output. |
| Outcome: | The proposed method achieves competitive performance with more harmful outputs. |
A Corpus for Visual Question Answering Annotated with Frame Semantic Information (2020.lrec-1)
Copied to clipboard
| Challenge: | Visual Question Answering (VQA) is a computer vision problem. |
| Approach: | They propose to annotate a visual question answering dataset with verb semantics to help the model understand verbs. |
| Outcome: | The proposed system is built on the imSitu dataset annotated with verb semantic information. |
Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer Approach (2025.acl-long)
Copied to clipboard
| Challenge: | Temporal information extraction from unstructured text is challenging due to complex clinical language, long documents, and sparse annotations. |
| Approach: | They propose a method for extracting clinical events and their temporal relations from unstructured text using the I2B2 2012 Temporal Relations Challenge corpus. |
| Outcome: | The proposed method improves state-of-the-art temporal information extraction with 5.5% improvement in tempeval F1 score over previous best and 8.9% improvement on long-range relations. |
Unveiling Performance Challenges of Large Language Models in Low-Resource Healthcare: A Demographic Fairness Perspective (2025.coling-main)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) are not effective in solving real-world healthcare tasks, but they are able to provide demographic information and provide biased health predictions. |
| Approach: | They evaluate state-of-the-art LLMs with three prevalent learning frameworks across six diverse healthcare tasks and find significant challenges in applying LLM to real-world healthcare tasks. |
| Outcome: | The proposed models perform poorly in real-world healthcare tasks and are inconsistent with existing learning frameworks. |
Towards Enhancing Health Coaching Dialogue in Low-Resource Settings (2022.coling-1)
Copied to clipboard
Yue Zhou, Barbara Di Eugenio, Brian Ziebart, Lisa Sharp, Bing Liu, Ben Gerber, Nikolaos Agadakos, Shweta Yadav
| Challenge: | Health coaching is cost-prohibitive due to its highly personalized nature. |
| Approach: | They propose to build a health coaching dialogue system that converses with patients . they propose to use simplified NLU and NLG frameworks and mechanism-conditioned empathetic response generation. |
| Outcome: | The proposed system generates more empathetic, fluent, and coherent responses . it outperforms the state-of-the-art in NLU tasks while requiring less annotations. |
Collaborative Data Exploration through Visualization: A Thesis Proposal Analyzing Impact of Conversational Assistants (2025.naacl-srw)
Copied to clipboard
| Challenge: | Data visualization is integral to any Exploratory Data Analysis task, but the steep learning curve and cognitive load of traditional tools excludes non-technical users. |
| Approach: | They propose to develop a conversational assistant capable of understanding user-initiated clarification requests and generating accurate responses to user requests. |
| Outcome: | The proposed conversational assistant can understand user-initiated clarification requests and generate accurate responses. |
The Curse of Verbalization: How Presentation Order Constrains LLM Reasoning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Xu et al., 2025) found that LLMs struggle when programs execute in an unaligned order. |
| Approach: | They propose to use esoteric programming languages to evaluate LLMs' reasoning abilities. |
| Outcome: | The proposed model improves reasoning performance across state-of-the-art models by restructuring problems to align the presentation order with the order of utilization. |
Augmenting Small Data to Classify Contextualized Dialogue Acts for Exploratory Visualization (2020.lrec-1)
Copied to clipboard
| Challenge: | a new corpus of conversations is being developed to support data visualization exploration . we use data augmentation to improve our methods for dialogue act classification . |
| Approach: | They propose to use a corpus of conversations to annotate contextualized dialogue acts . they highlight how thinking aloud affects interpretation of dialogue acts in the context . |
| Outcome: | The proposed AI can support visualization exploration with a small corpus of conversations . the proposed AI outperforms existing models in terms of performance and performance . |