← Back to all news
arXiv Computation and Language By Bj\"orn Nieth, Marianna Gracheva, Michaela Mahlberg, Bjoern Eskofier, Emmanuelle Salin

How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework

Read the original on arXiv Computation and Language →

The paper introduces a register-aware framework to evaluate how human-like large language models (LLMs) are, focusing on linguistic feature distributions rather than factual correctness. It uses Maximum Mean Discrepancy (MMD) and 67 Biber lexico‑grammatical features to compare LLM‑generated texts with human reference corpora across different registers. Experiments on seven instruction‑tuned, open‑source models across five English datasets show that all LLMs deviate from human baselines, with closeness to human language varying by register and not by model size.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Aug 26

The Limits of Automatic Evaluation of Creativity in Large Language Models

The paper examines whether existing automatic methods can reliably assess creativity in text produced by large language models (LLMs). By collecting human ratings on 11 creativity dimensions for both human and AI short stories, the authors compare these judgments with automated metrics and LLM-as-a-Judge evaluations. The results show a significant misalignment: automated metrics and LLM judges favor AI-generated stories and show near-zero correlation with human assessments, revealing fundamental limitations in current computational approaches to evaluating creative text.

By Alessandro Tutone, Giorgio Franceschelli, Mirco Musolesi
llmssafety
More like this →
arXiv AI
2d ago

Value Over Language Model: Detecting Original Contribution in Writing

The paper introduces VOLM, a framework that quantifies how much original value a human adds to a document beyond what a language model could generate from a task description alone. Unlike existing tools that focus on stylistic detection, VOLM extracts content at varying granularities, reconstructs it with an LLM, and compares these reconstructions to those derived from the task description. Evaluations across news articles, ICLR peer reviews, and argumentative essays show that VOLM can distinguish human-authored texts from LLM-generated ones while remaining robust to content-preserving transformations.

By Vibhhu Sharma, Thorsten Joachims, Sarah Dean
llms
More like this →