Holistic Evaluation of Language Models

Abstract

Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models. First, we taxonomize the vast space of potential scenarios (i.e. use cases) and metrics (i.e. desiderata) that are of interest for LMs. Then we select a broad subset based on coverage and feasibility, noting what's missing or underrepresented (e.g. question answering for neglected English dialects, metrics for trustworthiness). Second, we adopt a multi-metric approach: We measure 7 metrics (accuracy, calibration, robustness, fairness, bias, toxicity, and efficiency) for each of 16 core scenarios when possible (87.5% of the time). This ensures metrics beyond accuracy don't fall to the wayside, and that trade-offs are clearly exposed. We also perform 7 targeted evaluations, based on 26 targeted scenarios, to analyze specific aspects (e.g. reasoning, disinformation). Third, we conduct a large-scale evaluation of 30 prominent language models (spanning open, limited-access, and closed models) on all 42 scenarios, 21 of which were not previously used in mainstream LM evaluation. Prior to HELM, models on average were evaluated on just 17.9% of the core HELM scenarios, with some prominent models not sharing a single scenario in common. We improve this to 96.0%: now all 30 models have been densely benchmarked on the same core scenarios and metrics under standardized conditions. Our evaluation surfaces 25 top-level findings. For full transparency, we release all raw model prompts and completions publicly for further analysis, as well as a general modular toolkit. We intend for HELM to be a living benchmark for the community, continuously updated with new scenarios, metrics, and models.

Authored by the Center for Research on Foundation Models (CRFM) at the Stanford Institute for Human-Centered Artificial Intelligence (HAI). Project page: https://crfm.stanford.edu/helm/v1.0

Cited by in corpus (10)

• Large language models in medicine: the potentials and pitfalls
• Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data
• "We Need Structured Output": Towards User-centered Constraints on Large Language Model Output
• Evaluation and Benchmarking of LLM Agents: A Survey
• LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain
• LLM-Mediated Domain-Specific Voice Agents: The Case of TextileBot
• LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases
• On the attribution of confidence to large language models
• Quantifying the Uniqueness and Divisiveness of Presidential Discourse
• Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models