LLM Digest

Story

arxiv_cs_cl · Nov 10, 2026 · paper

Source brief

AI Isn't Getting Dumber, We're Getting Pickier: Rising Standards in Human Evaluation of Large Language Models

arxiv.orgNov 10, 2026
original source linked

In brief

Users often complain that AI assistants such as ChatGPT are getting worse. Some versions do change, but human evaluation leaves a second possibility untested: the people judging may change. We separate the two on Chatbot Arena, a public platform where people compare answers from

Read the original at arxiv.org →Open in live feed Read that day’s brief

AI Isn't Getting Dumber, We're Getting Pickier: Rising Standards in Human Evaluation of Large Language Models

Earlier in this thread 4 items

LM-SimBench: A Unified Framework, Dataset, and Benchmark for Large Language Model Training Simulation

Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning

Edith Harbaugh: Code Is Cheap. The Last Mile Isn't.

Framing-Induced Vulnerability in Large Language Models: Evidence from Chinese News Headlines