arXiv subjects

Ali Merali

Publications and source records attributed to Ali Merali.

3 recordsLinked to original sources

arXiv2026

A rubric-based controlled comparison of frontier language models on expert-authored clinical reasoning tasks

Multiple-choice medical benchmarks are increasingly saturated, and recent rubric-based evaluations such as HealthBench have shown that open-ended clinical performance is far from solved - its "Hard" subset top score remains 32%. We present a small, deliberately difficult evaluation dataset of five clinician-authored clinical scenarios spanning four specialties (anaesthesia, internal/family medicine, emergency medicine, and obstetrics), each accompanied by an atomic, weighted, MECE rubric (25-62 criteria per task; 184 criteria total) authored from a clinician-drafted golden answer. We evaluate three frontier models: GPT 5.4, Claude Opus 4.7, and Gemini 3.1 Pro. Mean rubric pass rates were 0.47 (Claude), 0.39 (GPT), and 0.37 (Gemini). The central finding is an inversion of clinical priority: the highest-weighted (weight-5, critical) criteria passed at only 32.4-41.7%, while low-stakes weight-1 criteria passed at 80-90%. 56 of 108 critical (weight-5) criteria (52%) were satisfied by no model. Three LLM autoraters reproduced expert met/not-met labels on 92.8-94.7% of 552 graded criteria. We position this as a methods-and-preliminary-findings contribution: the five tasks demonstrate a scalable, defensible pipeline ready to develop into a large-scale benchmark.

cs.AI↗

arXiv2025

Scaling Laws for Economic Productivity: Experimental Evidence in LLM-Assisted Consulting, Data Analyst, and Management Tasks

This paper derives `Scaling Laws for Economic Impacts' -- empirical relationships between the training compute of Large Language Models (LLMs) and professional productivity. In a preregistered experiment, over 500 consultants, data analysts, and managers completed professional tasks using one of 13 LLMs. We find that each year of AI model progress reduced task time by 8%, with 56% of gains driven by increased compute and 44% by algorithmic progress. However, productivity gains were significantly larger for non-agentic analytical tasks compared to agentic workflows requiring tool use. These findings suggest continued model scaling could boost U.S. productivity by approximately 20% over the next decade.

econ.GN↗

arXiv2024

Scaling Laws for Economic Productivity: Experimental Evidence in LLM-Assisted Translation

This paper derives "scaling laws"--empirical relationships between the training compute of Large Language Models (LLMs) and their performance--for economic outcomes. In a preregistered online experiment, 300 professional translators completed 1,800 tasks using one of 13 LLMs (or a control). A tenfold increase in model compute improved task completion speed by 12.3%, grades by 0.18 standard deviations, and earnings per minute by 16.1%. Gains were four times larger for lower-skilled workers. These findings suggest continued model scaling could boost U.S. productivity by at least 6.9% over the next decade.

econ.GN↗