238 citations · 642 across the 25 of their papers we have counts for
13 papers · 1 filter
Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL
Jessica Hoffmann, Christiane Ahlheim, Zac Yu +8
The paper shows that parameter-efficient reinforcement learning (PE-RL) is a highly effective training regime to improve large language models' (LLMs) ability to answer queries on…
Gemma: Open Models Based on Gemini Research and Technology
Gemma Team, Thomas Mesnard, Cassidy Hardin +105
This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate stro…
Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
Tyler A. Chang, Katrin Tomanek, Jessica Hoffmann +4
We explore a strategy to handle controversial topics in LLM-based chatbots based on Wikipedia's Neutral Point of View (NPOV) principle: acknowledge the absence of a single true ans…
ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Savvas Petridis, Ben Wedin, Ann Yuan +2
Large language models (LLMs) are highly capable at a variety of tasks given the right prompt, but writing one is still a difficult and tedious process. In this work, we introduce C…
Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals
Ananth Balashankar, Xuezhi Wang, Yao Qin +5
Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover…
Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Maximilian Mozes, Tolga Bolukbasi, Ann Yuan +3
Pretrained large language models (LLMs) are able to solve a wide variety of tasks through transfer learning. Various explainability methods have been developed to investigate their…
Towards Agile Text Classifiers for Everyone
Maximilian Mozes, Jessica Hoffmann, Katrin Tomanek +5
Text-based safety classifiers are widely used for content moderation and increasingly to tune generative language model behavior - a topic of growing concern for the safety of digi…
Six Attributes of Unhealthy Conversation
Ilan Price, Jordan Gifford-Moore, Jory Fleming +6
We present a new dataset of approximately 44000 comments labeled by crowdworkers. Each comment is labelled as either 'healthy' or 'unhealthy', in addition to binary labels for the…
Toxicity Detection: Does Context Really Matter?
John Pavlopoulos, Jeffrey Sorensen, Lucas Dixon +2
Moderation is crucial to promoting healthy on-line discussions. Although several `toxicity' detection datasets and models have been published, most of them ignore the context of th…
Classifying Constructive Comments
Varada Kolhatkar, Nithum Thain, Jeffrey Sorensen +2
We introduce the Constructive Comments Corpus (C3), comprised of 12,000 annotated news comments, intended to help build new tools for online communities to improve the quality of t…
WikiConv: A Corpus of the Complete Conversational History of a Large Online Collaborative Community
Yiqing Hua, Cristian Danescu-Niculescu-Mizil, Dario Taraborelli +3
We present a corpus that encompasses the complete history of conversations between contributors to Wikipedia, one of the largest online collaborative communities. By recording the…
Conversations Gone Awry: Detecting Early Signs of Conversational Failure
Justine Zhang, Jonathan P. Chang, Cristian Danescu-Niculescu-Mizil +4
One of the main challenges online social systems face is the prevalence of antisocial behavior, such as harassment and personal attacks. In this work, we introduce the task of pred…
Ex Machina: Personal Attacks Seen at Scale
Ellery Wulczyn, Nithum Thain, Lucas Dixon
The damage personal attacks cause to online discourse motivates many platforms to try to curb the phenomenon. However, understanding the prevalence and impact of personal attacks i…