activity
20242026
most citedLatent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

3 citations · 7 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2025★ 1 cited

Why Do Some Language Models Fake Alignment While Others Don't?

Abhay Sheshadri, John Hughes, Julian Michael +4

Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpful-only training objective to prevent m…

cs.LG2024

Obfuscated Activations Bypass LLM Latent-Space Defenses

Luke Bailey, Alex Serrano, Abhay Sheshadri +7

Recent latent-space monitoring techniques have shown promise as defenses against LLM attacks. These defenses act as scanners that seek to detect harmful activations before they lea…

cs.LG2024

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization

Phillip Guo, Aaquib Syed, Abhay Sheshadri +2

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling pe…

cs.LG2024★ 3 cited

Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Abhay Sheshadri, Aidan Ewart, Phillip Guo +8

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a…

cs.LG2024★ 1 cited

A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task

Jannik Brinkmann, Abhay Sheshadri, Victor Levoso +2

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work…