Benchmark Prediction with Sparse and Unpaired Cached Responses
cs.LG, stat.ME, stat.ML
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Consistent estimation of generative model representations in the data kernel perspective space
- Concentration bounds on response-based vector embeddings of black-box generative models
- Efficient Benchmarking Is Just Feature Selection and Multiple Regression
- Sparks of Artificial General Intelligence: Early experiments with GPT-4
- VCBench: Benchmarking LLMs in Venture Capital
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
- ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
- Training Verifiers to Solve Math Word Problems
- Comparing Foundation Models using Data Kernels
- LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
- Query-efficient model evaluation using cached responses
- Measuring Mathematical Problem Solving With the MATH Dataset
- Fluid Language Model Benchmarking
- FinanceBench: A New Benchmark for Financial Question Answering
- Gemini Embedding: Generalizable Embeddings from Gemini
- Active Evaluation Acquisition for Efficient LLM Benchmarking
- Holistic Evaluation of Language Models
- AgentBench: Evaluating LLMs as Agents
- RewardBench 2: Advancing Reward Model Evaluation
- tinyBenchmarks: evaluating LLMs with fewer examples
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis