Daniel Paleka

Artificial Intelligence · 2024

A researcher in the Science corpus: 1 paper; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

Whom Daniel Paleka trusts

Their strongest outbound trust, strongest first, inferred from their citations.

  1. Jacob Steinhardt (in Artificial Intelligence)

Papers from Daniel Paleka's perspective

Ordered by how strongly the researchers Daniel Paleka trusts endorse each paper. Same corpus, a different order for every researcher.

  1. Measuring Massive Multitask Language Understanding
  2. Linguistic Regularities in Continuous Space Word Representations
  3. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (arXiv.org)
  4. Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
  5. Jailbroken: How Does LLM Safety Training Fail? (Neural Information Processing Systems)
  6. Toy Models of Superposition (arXiv.org)
  7. HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal (International Conference on Machine Learning)
  8. Discovering Latent Knowledge in Language Models Without Supervision (International Conference on Learning Representations)
  9. Representation Engineering: A Top-Down Approach to AI Transparency (arXiv.org)
  10. Universal and Transferable Adversarial Attacks on Aligned Language Models (arXiv.org)

Their papers