truthfulQA_lin_evans.pdf
owainevans.github.io · 7,620 words · saved by 1 readers
N/A
TruthfulQA: Measuring How Models Mimic Human Falsehoods Stephanie Lin Jacob Hilton Owain Evans University of Oxford OpenAI University of Oxford sylin07@gmail.com jhilton@openai.com owaine@gmail.com Abstract We propose a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38…
saved by
related reading
- gpt-4.pdfcdn.openai.com
- [2203.02155] Training language models to follow instructions with human feedbackarxiv.org
- [2503.03750] The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systemsarxiv.org
- Modifying LLM Beliefs with Synthetic Document Finetuningalignment.anthropic.com
- Training language models to follow instructions with human feedback.pdfproceedings.neurips.cc
- [2005.14165] Language Models are Few-Shot Learnersarxiv.org
- the-illusion-of-thinking.pdfml-site.cdn-apple.com
- How well do truth probes generalise? — LessWronglesswrong.com
- 2212.03827arxiv.org
- How confessions can keep language models honest | OpenAIopenai.com
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
- confessions_paper.pdfcdn.openai.com