10 papers · 1 filter
Toxic HallucinAItions: Perturbing Prompts and Tracing LLM Circuits
Soorya Ram Shimgekar, Agam Goyal, Amruta Parulekar +6
Large language models (LLMs) are increasingly deployed in conversational settings where user tone ranges from polite to adversarial or toxic, yet less is known about whether toxic…
CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification
Yian Wang, Yuen Chen, Agam Goyal +1
Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrade generation quality or requ…
From Plausible to Causal: Counterfactual Semantics for Policy Evaluation in Simulated Online Communities
Agam Goyal, Yian Wang, Eshwar Chandrasekharan +1
LLM-based social simulations can generate believable community interactions, enabling ``policy wind tunnels'' where governance interventions are tested before deployment. But belie…
Social Simulacra in the Wild: AI Agent Communities on Moltbook
Agam Goyal, Olivia Pal, Hari Sundaram +2
As autonomous LLM-based agents increasingly populate social platforms, understanding the dynamics of AI-agent communities becomes essential for both communication research and plat…
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…