AIConfPaper
← Search

Anthony Rios

9 accepted papers

2025

A Multi-Agent Framework for Mitigating Dialect Biases in Privacy Policy Question-Answering Systems

Đorđe Klisura, Astrid R Bernaga Torres, Anna Karen Gárate-Escamilla, Rajesh Roshan Biswal, Ke Yang, Hilal Pataci +1
ACL 2025long

Privacy policies inform users about data collection and usage, yet their complexity limits accessibility for diverse populations. Existing Privacy Policy Question Answering (QA) systems exhibit performance disparities across English dialects, disadvantaging speakers of non-standard varieties. We pro…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Charting the Future: Using Chart Question-Answering for Scalable Evaluation of LLM-Driven Data Visualizations

James Ford, Xingmeng Zhao, Dan Schumacher, Anthony Rios
COLING 2025main

We propose a novel framework that leverages Visual Question Answering (VQA) models to automate the evaluation of LLM-generated data visualizations. Traditional evaluation methods often rely on human judgment, which is costly and unscalable, or focus solely on data accuracy, neglecting the effectiven…

Cited by 3Source ↗PDF ↗Scholar ↗
2025

Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach

James Ford, Anthony Rios
EMNLP 2025

Large language models can translate natural-language chart descriptions into runnable code, yet approximately 15% of the generated scripts still fail to execute, even after supervised fine-tuning and reinforcement learning. We investigate whether this persistent error rate stems from model limitatio

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction

Fatemeh Haji, Mazal Bethany, Cho-Yu Jason Chiang, Anthony Rios, Peyman Najafirad
EMNLP 2025

Event Extraction (EE) involves automatically identifying and extracting structured information about events from unstructured text, including triggers, event types, and arguments. Traditional discriminative models demonstrate high precision but often exhibit limited recall, particularly for nuanced

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems

Đorđe Klisura, Anthony Rios
NAACL 2025findings

Text-to-SQL systems empower users to interact with databases using natural language, automatically translating queries into executable SQL code. However, their reliance on database schema information for SQL generation exposes them to significant security vulnerabilities, particularly schema inferen…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

A Comprehensive Study of Gender Bias in Chemical Named Entity Recognition Models

Xingmeng Zhao, Ali Niazi, Anthony Rios
NAACL 2024long

Chemical named entity recognition (NER) models are used in many downstream tasks, from adverse drug reaction identification to pharmacoepidemiology. However, it is unknown whether these models work the same for everyone. Performance disparities can potentially cause harm rather than the intended goo…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

Extracting Biomedical Entities from Noisy Audio Transcripts

Nima Ebadi, Kellen Morgan, Adrian Tan, Billy Linares, Sheri Osborn, Emma Majors +2
COLING 2024main

Automatic Speech Recognition (ASR) technology is fundamental in transcribing spoken language into text, with considerable applications in the clinical realm, including streamlining medical transcription and integrating with Electronic Health Record (EHR) systems. Nevertheless, challenges persist, es…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2022

Measuring Geographic Performance Disparities of Offensive Language Classifiers

Brandon Lwowski, Paul Rad, Anthony Rios
COLING 2022main

Text classifiers are applied at scale in the form of one-size-fits-all solutions. Nevertheless, many studies show that classifiers are biased regarding different languages and dialects. When measuring and discovering these biases, some gaps present themselves and should be addressed. First, “Does la…

Cited by 5Source ↗PDF ↗Scholar ↗
2020

An Empirical Study of the Downstream Reliability of Pre-Trained Word Embeddings

Anthony Rios, Brandon Lwowski
COLING 2020main

While pre-trained word embeddings have been shown to improve the performance of downstream tasks, many questions remain regarding their reliability: Do the same pre-trained word embeddings result in the best performance with slight changes to the training data? Do the same pre-trained embeddings per…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗