KoLA: Carefully Benchmarking World Knowledge of Large Language Models
read the original abstract
The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations. Rather than merely exploring the breadth of LLM abilities, we believe meticulous and thoughtful designs are essential to thorough, unbiased, and applicable evaluations. Given the importance of world knowledge to LLMs, we construct a Knowledge-oriented LLM Assessment benchmark (KoLA), in which we carefully design three crucial factors: (1) For \textbf{ability modeling}, we mimic human cognition to form a four-level taxonomy of knowledge-related abilities, covering $19$ tasks. (2) For \textbf{data}, to ensure fair comparisons, we use both Wikipedia, a corpus prevalently pre-trained by LLMs, along with continuously collected emerging corpora, aiming to evaluate the capacity to handle unseen data and evolving knowledge. (3) For \textbf{evaluation criteria}, we adopt a contrastive system, including overall standard scores for better numerical comparability across tasks and models and a unique self-contrast metric for automatically evaluating knowledge-creating ability. We evaluate $28$ open-source and commercial LLMs and obtain some intriguing findings. The KoLA dataset and open-participation leaderboard are publicly released at https://kola.xlore.cn and will be continuously updated to provide references for developing LLMs and knowledge-related systems.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation
Text-to-image models show significant limitations in integrating world knowledge, as measured by the new WISE benchmark and WiScore metric across 20 models.
-
Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking
PAVE evaluates LLM verifiers across four pre-evidence epistemic states in RAG fact-checking, revealing model-dependent unreliable arbitration and proposing a JSD-based test-time method to improve reliability.
-
Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents
The thesis presents a kernel method for multiaccuracy across overlooked subpopulations, information-theoretic optimal watermarking for LLMs, and a simulator showing LLM agents outperforming humans in supply chains whi...
-
LWGR: Lagrangian-Constrained Personalized World Knowledge for Generative Recommendation
LWGR applies personalized soft instructions for LLM knowledge extraction and Lagrangian primal-dual optimization to selectively fuse beneficial world knowledge into generative recommendation while bounding degradation.
-
Agent AI: Surveying the Horizons of Multimodal Interaction
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.