paper-with-me

홈 › Papers

On the Implications of Verbose LLM Outputs: A Case Study in Translation Evaluation

2024-10-01 · Eleftheria Briakou, Zhongtao Liu, Colin Cherry, Markus Freitag

This paper investigates the impact of verbose LLM translations on evaluation. We first demonstrate the prevalence of this behavior across several LLM outputs drawn from the WMT 2024 general shared task on machine translation. We then identify the primary triggers of verbosity, including safety, copyright concerns, and insufficient context in short input queries. Finally, we show that ignoring this behavior unfairly penalizes more verbose LLMs according to both automatic and human evaluations, highlighting the need to address this issue for more accurate future evaluations.

📄 PDF Abstract BibTeX arXiv:2410.00863

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Similar Papers 제목 키워드 기반

SUMART: SUMmARizing Translation from Wordy to Concise Expression

2025-04-14 · Naoto Nishida, Jun Rekimoto

We propose SUMART, a method for summarizing and compressing the volume of verbose subtitle translations. SUMART is designed for understanding translated captions (e.g., interlingual conversations via subtitle translation…

Large Language ModelTranslation

Machine Translation Post-Editing (MTPE) from the Perspective of Translation Trainees: Implications for Translation Pedagogy

2021-08-01 · MTSummit 2021 8 · Dominika Cholewska

This paper introduces data on translation trainees’ perceptions of the MTPE process and implications on training in this field. This study aims to analyse trainees’ performance of three MTPE tasks the English-Polish lang…

Machine TranslationTranslation

NMT or SMT: Case Study of a Narrow-domain English-Latvian Post-editing Project

2017-11-01 · IJCNLP 2017 11 · Inguna Skadi{\c{n}}a, M{\=a}rcis Pinnis

The recent technological shift in machine translation from statistical machine translation (SMT) to neural machine translation (NMT) raises the question of the strengths and weaknesses of NMT. In this paper, we present a…

Machine TranslationNMTTranslation

An Image Is Worth Ten Thousand Words: Verbose-Text Induction Attacks on VLMs

2025-11-20 · Zhi Luo, Zenghui Yuan, Wenqi Wei, Daizong Liu 외 arxiv

With the remarkable success of Vision-Language Models (VLMs) on multimodal tasks, concerns regarding their deployment efficiency have become increasingly prominent. In particular, the number of tokens consumed during the…

Reinforcement LearningText Generation

Prompt Decorators: A Declarative and Composable Syntax for Reasoning, Formatting, and Control in LLMs

2025-10-21 · Mostapha Kalami Heris arxiv

Large Language Models (LLMs) are central to reasoning, writing, and decision-support workflows, yet users lack consistent control over how they reason and express outputs. Conventional prompt engineering relies on verbos…

Prompt Engineering