Search Results for author: Yejin Bang

Found 22 papers, 6 papers with code

The Pyramid of Captions

no code implementations1 May 2024 Delong Chen, Samuel Cahyawijaya, Etsuko Ishii, Ho Shu Chan, Yejin Bang, Pascale Fung

Building upon this foundation, we propose a novel Pyramid of Captions (PoCa) method, which constructs caption pyramids by generating localized captions for zoomed-in image patches and integrating them with global caption information using large language models.

Hallucination Image Captioning +1

High-Dimension Human Value Representation in Large Language Models

no code implementations11 Apr 2024 Samuel Cahyawijaya, Delong Chen, Yejin Bang, Leila Khalatbari, Bryan Wilie, Ziwei Ji, Etsuko Ishii, Pascale Fung

there is an urgent need to understand the scope and nature of human values injected into these models before their release.

Language Modelling

Measuring Political Bias in Large Language Models: What Is Said and How It Is Said

no code implementations27 Mar 2024 Yejin Bang, Delong Chen, Nayeon Lee, Pascale Fung

We propose to measure political bias in LLMs by analyzing both the content and style of their generated content regarding political issues.

Mitigating Framing Bias with Polarity Minimization Loss

no code implementations3 Nov 2023 Yejin Bang, Nayeon Lee, Pascale Fung

Framing bias plays a significant role in exacerbating political polarization by distorting the perception of actual events.

Document Summarization Multi-Document Summarization

Survey of Social Bias in Vision-Language Models

no code implementations24 Sep 2023 Nayeon Lee, Yejin Bang, Holy Lovenia, Samuel Cahyawijaya, Wenliang Dai, Pascale Fung

This survey aims to provide researchers with a high-level insight into the similarities and differences of social bias studies in pre-trained models across NLP, CV, and VL.


Learn What NOT to Learn: Towards Generative Safety in Chatbots

no code implementations21 Apr 2023 Leila Khalatbari, Yejin Bang, Dan Su, Willy Chung, Saeed Ghadimi, Hossein Sameti, Pascale Fung

Our approach differs from the standard contrastive learning framework in that it automatically obtains positive and negative signals from the safe and unsafe language distributions that have been learned beforehand.

Contrastive Learning

Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values

no code implementations14 Oct 2022 Yejin Bang, Tiezheng Yu, Andrea Madotto, Zhaojiang Lin, Mona Diab, Pascale Fung

Therefore, we introduce a framework for value-aligned classification that performs prediction based on explicitly written human values in the command.

Classification Few-Shot Learning +1

Towards Answering Open-ended Ethical Quandary Questions

no code implementations12 May 2022 Yejin Bang, Nayeon Lee, Tiezheng Yu, Leila Khalatbari, Yan Xu, Samuel Cahyawijaya, Dan Su, Bryan Wilie, Romain Barraud, Elham J. Barezi, Andrea Madotto, Hayden Kee, Pascale Fung

We explore the current capability of LLMs in providing an answer with a deliberative exchange of different perspectives to an ethical quandary, in the approach of Socratic philosophy, instead of providing a closed answer like an oracle.

Few-Shot Learning Generative Question Answering +2

NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias

1 code implementation NAACL 2022 Nayeon Lee, Yejin Bang, Tiezheng Yu, Andrea Madotto, Pascale Fung

Based on our discovery that title provides a good signal for framing bias, we present NeuS-TITLE that learns to neutralize news content in hierarchical order from title to article.

Decoder Multi-Task Learning +1

Survey of Hallucination in Natural Language Generation

no code implementations8 Feb 2022 Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Delong Chen, Ho Shu Chan, Wenliang Dai, Andrea Madotto, Pascale Fung

This advancement has led to more fluent and coherent NLG, leading to improved development in downstream tasks such as abstractive summarization, dialogue generation and data-to-text generation.

Abstractive Text Summarization Data-to-Text Generation +4

Assessing Political Prudence of Open-domain Chatbots

1 code implementation SIGDIAL (ACL) 2021 Yejin Bang, Nayeon Lee, Etsuko Ishii, Andrea Madotto, Pascale Fung

In this work, as a first step towards a politically safe chatbot, we propose a group of metrics for assessing their political prudence.


Weakly-supervised Multi-task Learning for Multimodal Affect Recognition

no code implementations23 Apr 2021 Wenliang Dai, Samuel Cahyawijaya, Yejin Bang, Pascale Fung

In this paper, we propose to leverage these datasets using weakly-supervised multi-task learning to improve the generalization performance on each of them.

Emotion Recognition Multi-Task Learning +1

Dynamically Addressing Unseen Rumor via Continual Learning

no code implementations18 Apr 2021 Nayeon Lee, Andrea Madotto, Yejin Bang, Pascale Fung

Rumors are often associated with newly emerging events, thus, an ability to deal with unseen rumors is crucial for a rumor veracity classification model.

Continual Learning Veracity Classification

Mitigating Media Bias through Neutral Article Generation

no code implementations1 Apr 2021 Nayeon Lee, Yejin Bang, Andrea Madotto, Pascale Fung

Media bias can lead to increased political polarization, and thus, the need for automatic mitigation methods is growing.

Towards Few-Shot Fact-Checking via Perplexity

no code implementations NAACL 2021 Nayeon Lee, Yejin Bang, Andrea Madotto, Madian Khabsa, Pascale Fung

Through experiments, we empirically verify the plausibility of the rather surprising usage of the perplexity score in the context of fact-checking and highlight the strength of our few-shot methodology by comparing it to strong fine-tuning-based baseline models.

Fact Checking Few-Shot Learning +5

Model Generalization on COVID-19 Fake News Detection

no code implementations11 Jan 2021 Yejin Bang, Etsuko Ishii, Samuel Cahyawijaya, Ziwei Ji, Pascale Fung

Amid the pandemic COVID-19, the world is facing unprecedented infodemic with the proliferation of both fake and real information.

Fake News Detection Misinformation

The Adapter-Bot: All-In-One Controllable Conversational Model

1 code implementation28 Aug 2020 Andrea Madotto, Zhaojiang Lin, Yejin Bang, Pascale Fung

The dialogue skills can be triggered automatically via a dialogue manager, or manually, thus allowing high-level control of the generated responses.

Movie Recommendation

Misinformation Has High Perplexity

1 code implementation8 Jun 2020 Nayeon Lee, Yejin Bang, Andrea Madotto, Pascale Fung

Debunking misinformation is an important and time-critical task as there could be adverse consequences when misinformation is not quashed promptly.

Language Modelling Misinformation +3

XPersona: Evaluating Multilingual Personalized Chatbot

1 code implementation EMNLP (NLP4ConvAI) 2021 Zhaojiang Lin, Zihan Liu, Genta Indra Winata, Samuel Cahyawijaya, Andrea Madotto, Yejin Bang, Etsuko Ishii, Pascale Fung

Experimental results show that the multilingual trained models outperform the translation-pipeline and that they are on par with the monolingual models, with the advantage of having a single model across multiple languages.

Chatbot Translation

Understanding the Shades of Sexism in Popular TV Series

no code implementations WS 2019 Nayeon Lee, Yejin Bang, Jamin Shin, Pascale Fung

[Multiple-submission] In the midst of a generation widely exposed to and influenced by media entertainment, the NLP research community has shown relatively little attention on the sexist comments in popular TV series.


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