5 papers
Introspection Adapters: Training LLMs to Report Their Learned Behaviors
Keshav Shenoy, Li Yang, Abhay Sheshadri +4
When model developers or users fine-tune an LLM, this can induce behaviors that are unexpected, deliberately harmful, or hard to detect. It would be far easier to audit LLMs if the…
AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
Abhay Sheshadri, Aidan Ewart, Kai Fronsdal +5
We introduce AuditBench, an alignment auditing benchmark. AuditBench consists of 56 language models with implanted hidden behaviors. Each model has one of 14 concerning behaviors--…
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…
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…
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…