AI models' writing becomes predictable, but judging taste doesn't improve

By PulseAugur Editorial · [1 sources] · 2026-10-23 04:00

A new study published on arXiv investigates how post-training affects language models' writing style and their ability to judge creative content. Researchers found that while training makes models' own writing more predictable, it does not significantly improve their taste or ability to judge creative writing. In fact, trained models showed a preference for predictable writing and became more influenced by factors like story length and order, even failing to distinguish a story from its scrambled words. AI

IMPACT This research suggests that current training methods may inadvertently lead AI models to favor predictable outputs, potentially hindering their creative capabilities and objective evaluation.

RANK_REASON The cluster contains an academic paper detailing research findings on language model behavior. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI models' writing becomes predictable, but judging taste doesn't improve

How we ranked this

Signal score: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; The cluster contains an academic paper detailing research findings on language model behavior. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

arXiv cs.CL TIER_1 English(EN) · Arman Nik Khah, Arvin Bahreini · 2026-10-23 04:00

Is the Judge Its Twin? Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing

arXiv:2609.32196v2 Announce Type: replace Abstract: Language models now routinely grade other language models. If post-training makes a model's writing more predictable, it may also teach the same model, as a judge, to reward predictable writing. We test this directly. We follow …

How we ranked this

COVERAGE [1]

Is the Judge Its Twin? Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing

RELATED ENTITIES

RELATED TOPICS