Entity · benchmark

Epanorthosis Index

benchmarkactiveprovisionalepanorthosis-index-fef3083e·1 events·first seen Jul 24, 2026

Aliases: Epanorthosis Index

Co-occurring entities

LoRA Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it

More like this (12)

C-index Anthropic Economic Index EpiCurveSimilarity OEIS Conjectures Persuasion Index Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it Artificial Analysis Intelligence Index Ramp AI Index Index Sickness Trajectory Deviation Index Exact Posterior Score Epi2Diff

Recent events (1)

4arXiv · cs.CL·Jul 24, 2026·source ↗

Artificial Epanorthosis: LLMs systematically overuse a classical rhetorical self-correction figure, study finds

A new arXiv paper identifies that large language models systematically overuse 'epanorthosis' — a rhetorical self-correction figure (e.g., 'This is not a course. It is a journey of transformation') — attributing the pattern to training data rich in promotional prose and RLHF preference tuning that rewards emphatic phrasing. The authors introduce an Epanorthosis Index to measure deviation from genre-specific human baselines, finding models overshoot in oratory (up to threefold in Italian) and undershoot in informal Q&A. Mitigation experiments show a one-line instruction cuts the figure by 50–75%, while a LoRA fine-tuning adapter nearly eliminates it, with the stated goal being calibration to human rates rather than elimination.

Evaluation and Benchmarking Alignment and RLHF Epanorthosis Index LoRA Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it