Search Results for author:
Found 8 papers, 5 papers with code
How Do Large Language Monkeys Get Their Power (Laws)?
Recent research across mathematical problem solving, proof assistant programming and multimodal jailbreaking documents a striking finding: when (multimodal) language model tackle a suite of tasks with multiple attempts per task -- succeeding if any attempt is correct -- then the negative log of the average success rate scales a power law in the number of attempts.
Best-of-N Jailbreaking
We find that BoN Jailbreaking achieves high attack success rates (ASRs) on closed-source language models, such as 89% on GPT-4o and 78% on Claude 3. 5 Sonnet when sampling 10, 000 augmented prompts.
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful text from models that were fine-tuned to be harmless.
Analyzing the Generalization and Reliability of Steering Vectors
In this work, we rigorously investigate these properties, and show that steering vectors have substantial limitations both in- and out-of-distribution.
Eight Methods to Evaluate Robust Unlearning in LLMs
Machine unlearning can be useful for removing harmful capabilities and memorized text from large language models (LLMs), but there are not yet standardized methods for rigorously evaluating it.
Towards Automated Circuit Discovery for Mechanistic Interpretability
For example, the ACDC algorithm rediscovered 5/5 of the component types in a circuit in GPT-2 Small that computes the Greater-Than operation.
Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases
The problem of spurious correlations (SCs) arises when a classifier relies on non-predictive features that happen to be correlated with the labels in the training data.
Causal Machine Learning: A Survey and Open Problems
Causal Machine Learning (CausalML) is an umbrella term for machine learning methods that formalize the data-generation process as a structural causal model (SCM).
