activity
20242026
collaborators

8 papers

cs.AI2026

AI Organizations are More Effective but Less Aligned than Individual Agents

Judy Hanwen Shen, Daniel Zhu, Siddarth Srinivasan +5

AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that multi-agent "AI organizatio…

cs.LG2026

Abstractive Red-Teaming of Language Model Character

Nate Rahn, Allison Qi, Avery Griffin +3

We want language model assistants to conform to a character specification, which asserts how the model should act across diverse user interactions. While models typically follow th…

cs.CR2026

Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs

Jackson Kaunismaa, Avery Griffin, John Hughes +3

Model developers implement safeguards in frontier models to prevent misuse, for example, by employing classifiers to filter dangerous outputs. In this work, we demonstrate that eve…

cs.LG2025

Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs

Igor Shilov, Alex Cloud, Aryo Pradipta Gema +5

Large Language Models increasingly possess capabilities that carry dual-use risks. While data filtering has emerged as a pretraining-time mitigation, it faces significant challenge…

cs.LG2025

Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

Alexandra Souly, Javier Rando, Ed Chapman +10

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoni…

cs.AI2025

How Do Large Language Monkeys Get Their Power (Laws)?

Rylan Schaeffer, Joshua Kazdan, John Hughes +7

Recent research across mathematical problem solving, proof assistant programming and multimodal jailbreaking documents a striking finding: when (multimodal) language model tackle a…