Search Results for author:
Found 21 papers, 6 papers with code
High-Dimension Human Value Representation in Large Language Models
there is an urgent need to understand the scope and nature of human values injected into these models before their release.
Measuring Political Bias in Large Language Models: What Is Said and How It Is Said
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
Framing bias plays a significant role in exacerbating political polarization by distorting the perception of actual events.
Survey of Social Bias in Vision-Language Models
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
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.
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
It is, for example, better at deductive than inductive reasoning.
Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustness
Developing robust and fair AI systems require datasets with comprehensive set of labels that can help ensure the validity and legitimacy of relevant measurements.
Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values
Therefore, we introduce a framework for value-aligned classification that performs prediction based on explicitly written human values in the command.
Towards Answering Open-ended Ethical Quandary Questions
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.
NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias
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.
Survey of Hallucination in Natural Language Generation
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.
Assessing Political Prudence of Open-domain Chatbots
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
In this paper, we propose to leverage these datasets using weakly-supervised multi-task learning to improve the generalization performance on each of them.
Dynamically Addressing Unseen Rumor via Continual Learning
Rumors are often associated with newly emerging events, thus, an ability to deal with unseen rumors is crucial for a rumor veracity classification model.
Mitigating Media Bias through Neutral Article Generation
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
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.
Model Generalization on COVID-19 Fake News Detection
Amid the pandemic COVID-19, the world is facing unprecedented infodemic with the proliferation of both fake and real information.
The Adapter-Bot: All-In-One Controllable Conversational Model
The dialogue skills can be triggered automatically via a dialogue manager, or manually, thus allowing high-level control of the generated responses.
Misinformation Has High Perplexity
Debunking misinformation is an important and time-critical task as there could be adverse consequences when misinformation is not quashed promptly.
XPersona: Evaluating Multilingual Personalized Chatbot
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.
Understanding the Shades of Sexism in Popular TV Series
[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.
