1 citations · 1 across the 9 of their papers we have counts for
9 papers
Facts Without Rules: Boundary Metadata Collapse in Multi-Agent LLM Handoffs
Yian Wang, Agam Goyal, Eshwar Chandrasekharan +1
Multi-agent LLM systems often coordinate by compressing an upstream interaction into a handoff artifact that downstream agents treat as shared state. We show that this handoff step…
Prompt PerturbAItions: Mechanisms of LLM Response Inconsistencies
Soorya Ram Shimgekar, Agam Goyal, Amruta Parulekar +6
Large language models (LLMs) are increasingly deployed in conversational settings where user phrasing ranges from polite to casual to toxic, yet less is known about whether such le…
State Contamination in Memory-Augmented LLM Agents
Yian Wang, Agam Goyal, Yuen Chen +1
LLM agents increasingly rely on persistent state, including transcripts, summaries, retrieved context, and memory buffers, to support long-horizon interaction. This makes safety de…
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…
DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
Yuen Chen, Yian Wang, Hari Sundaram
The goal of this paper is to accelerate the training of machine learning models, a critical challenge since the training of large-scale deep neural models can be computationally ex…
The Chilling: Identifying Strategic Antisocial Behavior Online and Examining the Impact on Journalists
Yian Wang, Mukhilshankar Umashankar, Eshwar Chandrasekharan +1
On social platforms like Twitter, strategic targeted attacks are becoming increasingly common, especially against vulnerable groups such as female journalists. Two key challenges i…
On the Necessity of Output Distribution Reweighting for Effective Class Unlearning
Ali Ebrahimpour-Boroojeny, Yian Wang, Hari Sundaram
In this paper, we reveal a significant shortcoming in class unlearning evaluations: overlooking the underlying class geometry can cause information leakage about the forgotten clas…
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…