Search Results for author:
Found 10 papers, 5 papers with code
A Systematic Analysis of Base Model Choice for Reward Modeling
In this work, we present a systematic analysis of the effect of base model selection on reward modeling performance.
KULCQ: An Unsupervised Keyword-based Utterance Level Clustering Quality Metric
Intent discovery is crucial for both building new conversational agents and improving existing ones.
Don't Blame the Data, Blame the Model: Understanding Noise and Bias When Learning from Subjective Annotations
Researchers have raised awareness about the harms of aggregating labels especially in subjective tasks that naturally contain disagreements among human annotators.
Reading Between the Tweets: Deciphering Ideological Stances of Interconnected Mixed-Ideology Communities
Recent advances in NLP have improved our ability to understand the nuanced worldviews of online communities.
Capturing Perspectives of Crowdsourced Annotators in Subjective Learning Tasks
Previous studies have shed light on the pitfalls of label aggregation and have introduced a handful of practical approaches to tackle this issue.
A Data Fusion Framework for Multi-Domain Morality Learning
Language models can be trained to recognize the moral sentiment of text, creating new opportunities to study the role of morality in human life.
Noise Audits Improve Moral Foundation Classification
Morality classification relies on human annotators to label the moral expressions in text, which provides training data to achieve state-of-the-art performance.
Infusing Knowledge from Wikipedia to Enhance Stance Detection
Stance detection infers a text author's attitude towards a target.
Detecting Polarized Topics Using Partisanship-aware Contextualized Topic Embeddings
We apply our method to a dataset of news articles about the COVID-19 pandemic.
Challenges in Forecasting Malicious Events from Incomplete Data
As we show in this paper, the process of filtering reduces the predictability of cyber-attacks.
