Any single-output LLM ensemble is accuracy-capped at 1-beta where beta is the all-models-wrong rate, a quantity not captured by pairwise correlations and frequently underestimated by copula models.
Cost-of-Pass: An economic framework for evaluating language models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
Curating concise data for VLMs induces brevity, delivering 35x lower Cost-of-Pass at near-identical accuracy and higher matched-length accuracy than uncurated baselines.
Empirical study finds Progressive Disclosure raises distinct resources touched (1.18 to 3.85) and uptake events (1.33 to 3.92) per trajectory, adds 17 passing trials out of 410 (+4.1%), with gains task-dependent.
LCAE is introduced as a Rasch-model metric that aligns LLM self-reported confidence with latent error probability derived from ability and item difficulty, shown to improve calibration on a medical dataset across 20 models.
DDS introduces typed contracts at intent, operator DAG, skills, and runtime layers to bound agentic search for data system compositions, achieving convergence on a trading workload where unbounded iteration fails.
RAG is more effective and cost-efficient than fine-tuning for industrial QA adaptation on automotive datasets.
citing papers explorer
-
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
Any single-output LLM ensemble is accuracy-capped at 1-beta where beta is the all-models-wrong rate, a quantity not captured by pairwise correlations and frequently underestimated by copula models.
-
Brevity is the Soul of Inference Efficiency: Inducing Concision in VLMs via Data Curation
Curating concise data for VLMs induces brevity, delivering 35x lower Cost-of-Pass at near-identical accuracy and higher matched-length accuracy than uncurated baselines.
-
SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior
Empirical study finds Progressive Disclosure raises distinct resources touched (1.18 to 3.85) and uptake events (1.33 to 3.92) per trajectory, adds 17 passing trials out of 410 (+4.1%), with gains task-dependent.
-
Latent Confidence Alignment for LLM Self-Assessment
LCAE is introduced as a Rasch-model metric that aligns LLM self-reported confidence with latent error probability derived from ability and item difficulty, shown to improve calibration on a medical dataset across 20 models.
-
Declarative Data Services: Structured Agentic Discovery for Composing Data Systems
DDS introduces typed contracts at intent, operator DAG, skills, and runtime layers to bound agentic search for data system compositions, achieving convergence on a trading workload where unbounded iteration fails.
-
Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications
RAG is more effective and cost-efficient than fine-tuning for industrial QA adaptation on automotive datasets.