Search Results for author:
Found 16 papers, 12 papers with code
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
To measure these risks of malicious use, government institutions and major AI labs are developing evaluations for hazardous capabilities in LLMs.
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigorously assess new methods.
Representation Engineering: A Top-Down Approach to AI Transparency
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience.
Ranked #3 on
Question Answering
on TruthfulQA
Universal and Transferable Adversarial Attacks on Aligned Language Models
Specifically, our approach finds a suffix that, when attached to a wide range of queries for an LLM to produce objectionable content, aims to maximize the probability that the model produces an affirmative response (rather than refusing to answer).
Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
And how do we measure these behaviors in general-purpose models such as GPT-4?
Papaya: Federated Learning, but Fully Decentralized
Federated Learning systems use a centralized server to aggregate model updates.
Unlocking Deterministic Robustness Certification on ImageNet
We show that fast ways of bounding the Lipschitz constant for conventional ResNets are loose, and show how to address this by designing a new residual block, leading to the \emph{Linear ResNet} (LiResNet) architecture.
How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
In experiments, we show how video models that are primarily trained to recognize actions and find contours of objects can be repurposed to understand human preferences and the emotional content of videos.
Forecasting Future World Events with Neural Networks
We test language models on our forecasting task and find that performance is far below a human expert baseline.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy.
What Would Jiminy Cricket Do? Towards Agents That Behave Morally
When making everyday decisions, people are guided by their conscience, an internal sense of right and wrong.
Improving and Assessing Anomaly Detectors for Large-Scale Settings
We conduct extensive experiments in these more realistic settings for out-of-distribution detection and find that a surprisingly simple detector based on the maximum logit outperforms prior methods in all the large-scale multi-class, multi-label, and segmentation tasks, establishing a simple new baseline for future work.
How Multipurpose Are Language Models?
By comprehensively evaluating the breadth and depth of a model's academic and professional understanding, our test can be used to analyze models across many tasks and to identify important shortcomings.
Measuring Massive Multitask Language Understanding
By comprehensively evaluating the breadth and depth of a model's academic and professional understanding, our test can be used to analyze models across many tasks and to identify important shortcomings.
Ranked #60 on
Multi-task Language Understanding
on MMLU
Scaling Out-of-Distribution Detection for Real-World Settings
We conduct extensive experiments in these more realistic settings for out-of-distribution detection and find that a surprisingly simple detector based on the maximum logit outperforms prior methods in all the large-scale multi-class, multi-label, and segmentation tasks, establishing a simple new baseline for future work.
