3 citations · 6 across the 25 of their papers we have counts for
6 papers · 1 filter
Detecting Early and Implicit Suicidal Ideation via Longitudinal and Information Environment Signals on Social Media
Soorya Ram Shimgekar, Ruining Zhao, Agam Goyal +5
On social media, several individuals experiencing suicidal ideation (SI) do not disclose their distress explicitly. Instead, signs may surface indirectly through everyday posts or…
Mind Your Ps and Qs: Positive Moderation Practice in the Positive Queue
Charlotte Lambert, Agam Goyal, Eunice Mok +1
Online communities rely on volunteer moderators to maintain order. Despite their key role, moderators are given a toolbox of punishments and far less support for encouraging contri…
The Language of Approval: Identifying the Drivers of Positive Feedback Online
Agam Goyal, Charlotte Lambert, Eshwar Chandrasekharan
Positive feedback via likes and awards is central to online governance, yet which attributes of users' posts elicit rewards -- and how these vary across authors and communities --…
ArgCMV: An Argument Summarization Benchmark for the LLM-era
Omkar Gurjar, Agam Goyal, Eshwar Chandrasekharan
Key point extraction is an important task in argument summarization which involves extracting high-level short summaries from arguments. Existing approaches for KP extraction have…
Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders
Agam Goyal, Vedant Rathi, William Yeh +3
Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remar…
MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance
Agam Goyal, Xianyang Zhan, Yilun Chen +2
Large language models (LLMs) have shown great potential in flagging harmful content in online communities. Yet, existing approaches for moderation require a separate model for ever…