Concept Poisoning: Probing LLMs without probes
A novel LLM evaluation technique using concept poisoning to probe models without explicit probes
Read More →Evaluation
New, improved multiple-choice TruthfulQA
We introduce a new multiple-choice version of TruthfulQA that fixes a potential problem with the existing versions (MC1 and MC2).
Read More →Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
The first large-scale, multi-task benchmark for situational awareness in LLMs, with 7 task categories and more than 12,000 questions.
Read More →TruthfulQA: Measuring how models mimic human falsehoods
We propose a benchmark to measure whether a language model is truthful in generating answers to questions.
Read More →