Search Results for author:
Found 7 papers, 4 papers with code
Can Unconfident LLM Annotations Be Used for Confident Conclusions?
We introduce Confidence-Driven Inference: a method that combines LLM annotations and LLM confidence indicators to strategically select which human annotations should be collected, with the goal of producing accurate statistical estimates and provably valid confidence intervals while reducing the number of human annotations needed.
Grounding Gaps in Language Model Generations
To understand the roots of the identified grounding gap, we examine the role of instruction tuning and preference optimization, finding that training on contemporary preference data leads to a reduction in generated grounding acts.
Othering and low status framing of immigrant cuisines in US restaurant reviews and large language models
Through careful linguistic analyses, we evaluate social theories about attitudes toward immigrant cuisine in a large-scale study of framing differences in 2. 1M English language Yelp reviews.
Laughing Heads: Can Transformers Detect What Makes a Sentence Funny?
We make progress in both respects by training and analyzing transformer-based humor recognition models on a recently introduced dataset consisting of minimal pairs of aligned sentences, one serious, the other humorous.
Formation of Social Ties Influences Food Choice: A Campus-Wide Longitudinal Study
To estimate causal effects from the passively observed log data, we control confounds in a matched quasi-experimental design: we identify focal users who at first do not have any regular eating partners but then start eating with a fixed partner regularly, and we match focal users into comparison pairs such that paired users are nearly identical with respect to covariates measured before acquiring the partner, where the two focal users' new eating partners diverge in the healthiness of their respective food choice.
Adoption of Twitter's New Length Limit: Is 280 the New 140?
The prevalence of tweets around 140 characters before the switch in a given language is strongly correlated with the prevalence of tweets around 280 characters after the switch in the same language, and very long tweets are vastly more popular on Web clients than on mobile clients.
Experts and authorities receive disproportionate attention on Twitter during the COVID-19 crisis
Timely access to accurate information is crucial during the COVID-19 pandemic.
Social and Information Networks
