Reports examine LLM reasoning, provable inference, and authorship impersonation

This story is from 2026-11-04. It is preserved in the archive; the latest stories are on the live feed.

New research covers benchmarking LLMs on alloy property prediction with out-of-distribution severity metrics, progress on provable inference for LLMs, and a comparative evaluation of six models' ability to impersonate individual authors.

Read the full story at arXiv cs.LG ↗

Timeline · 3 reports

1. 2026-11-06 05:00 · arXiv cs.CL
   How Well Can Large Language Models Impersonate Individual Authors? A Comparative Evaluation
2. 2026-11-04 17:17 · Hacker News Front Page
   Progress on provable inference for large language models
3. 2026-11-04 05:00 · arXiv cs.LG
   Quantifying out-of-distribution data severity with Wasserstein distances: benchmarking large language models for alloy property prediction