How Can I Publish My LLM Benchmark Without Giving the True Answers Away?
Publishing a large language model (LLM) benchmark on the Internet risks contaminating future LLMs: the benchmark may be unintentionally (or intentionally) used to train or select a model. A common mitigation is to keep the benchmark private and let participants submit their models or predictions to the organizers. However, this strategy will require trust in a single organization and still permits test-set overfitting through repeated queries. To overcome this issue, we propose a way to publish benchmarks without completely disclosing the ground-truth answers to the questions, while still maintaining the ability to openly evaluate LLMs. Our main idea is to inject randomness to the answers by preparing several logically correct answers, and only include one of them as the solution in the benchmark. This reduces the best possible accuracy, i.e., Bayes accuracy, of the benchmark. Not only is this helpful to keep us from disclosing the ground truth, but this approach also offers a test for detecting data contamination. In principle, even fully capable models should not surpass the Bayes accuracy. If a model surpasses this ceiling despite this expectation, this is a strong signal of data contamination. We present experimental evidence that our method can detect data contamination accurately on a wide range of benchmarks, models, and training methodologies.
Code (0)
등록된 구현이 없습니다.
Tasks
Large Language ModelSimilar Papers 제목 키워드 기반
Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpr…
Multiple-choiceDevelopment of a Reliable and Accessible Caregiving Language Model (CaLM)
Unlike professional caregivers, family caregivers often assume this role without formal preparation or training. Because of this, there is an urgent need to enhance the capacity of family caregivers to provide quality ca…
Language ModelingLanguage ModellingRAGRetrieval-augmented GenerationAlexpaca: Learning Factual Clarification Question Generation Without Examples
Real-life tasks such as giving legal or technical advice often lack complete context at the outset and can have disparate answers depending thereon. The ability to derive missing factual information by asking clarifying …
BenchmarkingChatbotQuestion AnsweringQuestion Generation+1CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks
Selecting a pretrained language model, or evaluating a fine-tuned one, for a specific application is a high-value decision, yet the public benchmarks used to make it are poorly suited: a generic benchmark need not reflec…
Hashmarks: Privacy-Preserving Benchmarks for High-Stakes AI Evaluation
There is a growing need to gain insight into language model capabilities that relate to sensitive topics, such as bioterrorism or cyberwarfare. However, traditional open source benchmarks are not fit for the task, due to…
FormLanguage ModelingLanguage ModellingPrivacy Preserving