AI Paper Atlas

Research map / Large language models / AI and society

Counterfactual LLM-based Framework for Measuring Rhetorical Style

Jingyi Qiu, Hong Chen, Zongyi Li

ICLR 2026 · Large language models › AI and society · approach: Data commons and human baselines · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use counterfactual BT rhetorical score as predictor instead of direct LLM ratingcitation regression · ICLR 2017-2025 citationsregression coefficient: -26.11 -> 24.53Improved
use counterfactual BT rhetorical score instead of promotion lexicon scoremedia posts regression · ICLR postsregression coefficient: 0.64 -> 3.19Improved
higher rhetorical scorepaper attention · ICLR citationsregression coefficient: +24.53 citations per unitImproved
higher rhetorical scorepeer review rating · ICLR average reviewer scoreSpearman correlation: rho = -0.015, p = 0.225No clear effect
increase number of personas from 8 to 15 in panel (ablation)rhetorical scores · ICLR 8,485 abstractsSpearman with full panel: 0.89 -> 0.958Improved
replace persona subset with a disjoint subset (ablation)rhetorical scores · ICLR abstractsSpearman correlation: mean 0.89No clear effect
year 2023 onward vs 2018-2022mean rhetorical score · ICLR submissionsrhetorical scoreHurt
higher estimated LLM usage in abstractsrhetorical score · ICLR 2024-2025estimated LLM usage (%): 9.0% -> 20.9%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy