Search Results for author: Amanda Cercas Curry

Found 21 papers, 8 papers with code

Conversational Assistants and Gender Stereotypes: Public Perceptions and Desiderata for Voice Personas

no code implementations GeBNLP (COLING) 2020 Amanda Cercas Curry, Judy Robertson, Verena Rieser

We then outline a multi-disciplinary project of how we plan to address the complex question of gender and stereotyping in digital assistants.

Multiple-choice

ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Detection in Conversational AI

no code implementations EMNLP 2021 Amanda Cercas Curry, Gavin Abercrombie, Verena Rieser

We find that the distribution of abuse is vastly different compared to other commonly used datasets, with more sexually tinted aggression towards the virtual persona of these systems.

Abusive Language Chatbot

Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate

1 code implementation4 Jun 2025 Mikel K. Ngueajio, Flor Miriam Plaza-del-Arco, Yi-Ling Chung, Danda B. Rawat, Amanda Cercas Curry

Automated counter-narratives (CN) offer a promising strategy for mitigating online hate speech, yet concerns about their affective tone, accessibility, and ethical risks remain.

Language Modeling Language Modelling +1

The AI Gap: How Socioeconomic Status Affects Language Technology Interactions

no code implementations17 May 2025 Elisa Bassignana, Amanda Cercas Curry, Dirk Hovy

Our findings suggest that while generative language technologies are becoming more accessible to everyone, socioeconomic linguistic differences still stratify their use to exacerbate the digital divide.

Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks

1 code implementation12 Jun 2024 Justin Zhao, Flor Miriam Plaza-del-Arco, Benjie Genchel, Amanda Cercas Curry

However, using a single LLM judge is prone to intra-model bias, and many tasks - such as those related to emotional intelligence, creative writing, and persuasiveness - may be too subjective for a single model to judge fairly.

Benchmarking Chatbot +4

Impoverished Language Technology: The Lack of (Social) Class in NLP

no code implementations6 Mar 2024 Amanda Cercas Curry, Zeerak Talat, Dirk Hovy

Since Labov's (1964) foundational work on the social stratification of language, linguistics has dedicated concerted efforts towards understanding the relationships between socio-demographic factors and language production and perception.

Subjective $\textit{Isms}$? On the Danger of Conflating Hate and Offence in Abusive Language Detection

no code implementations4 Mar 2024 Amanda Cercas Curry, Gavin Abercrombie, Zeerak Talat

Natural language processing research has begun to embrace the notion of annotator subjectivity, motivated by variations in labelling.

Abusive Language Hate Speech Detection +2

Emotion Analysis in NLP: Trends, Gaps and Roadmap for Future Directions

1 code implementation2 Mar 2024 Flor Miriam Plaza-del-Arco, Alba Curry, Amanda Cercas Curry, Dirk Hovy

We then discuss four lacunae: (1) the absence of demographic and cultural aspects does not account for the variation in how emotions are perceived, but instead assumes they are universally experienced in the same manner; (2) the poor fit of emotion categories from the two main emotion theories to the task; (3) the lack of standardized EA terminology hinders gap identification, comparison, and future goals; and (4) the absence of interdisciplinary research isolates EA from insights in other fields.

Emotion Recognition

Know Your Audience: Do LLMs Adapt to Different Age and Education Levels?

no code implementations4 Dec 2023 Donya Rooein, Amanda Cercas Curry, Dirk Hovy

We find large variations in the readability of the answers by different LLMs.

Mirages: On Anthropomorphism in Dialogue Systems

no code implementations16 May 2023 Gavin Abercrombie, Amanda Cercas Curry, Tanvi Dinkar, Verena Rieser, Zeerak Talat

In this paper, we discuss the linguistic factors that contribute to the anthropomorphism of dialogue systems and the harms that can arise, including reinforcing gender stereotypes and notions of acceptable language.

Computer says "No": The Case Against Empathetic Conversational AI

no code implementations21 Dec 2022 Alba Curry, Amanda Cercas Curry

Emotions are an integral part of human cognition and they guide not only our understanding of the world but also our actions within it.

ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI

1 code implementation20 Sep 2021 Amanda Cercas Curry, Gavin Abercrombie, Verena Rieser

We find that the distribution of abuse is vastly different compared to other commonly used datasets, with more sexually tinted aggression towards the virtual persona of these systems.

Abuse Detection Abusive Language +1

A Review of Evaluation Techniques for Social Dialogue Systems

no code implementations13 Sep 2017 Amanda Cercas Curry, Helen Hastie, Verena Rieser

In contrast with goal-oriented dialogue, social dialogue has no clear measure of task success.

valid

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