The study introduces a zero‑shot benchmark for eight large language models on English and Bengali abstractive summarization, using both lexical/semantic metrics and reference‑free factuality checks. Results show significant cross‑lingual differences: GPT‑5.6 Luna excels in English but not in Bengali, where LLaMA 3.3 70B tops ROUGE and BLEU, while Gemini 2.5 Flash achieves the best Bengali factuality score. The evaluation also reveals that different metrics rank models differently, underscoring the need for multi‑dimensional assessment in low‑resource languages.
By Khan Mahi Al Atahar, Nazifa Tasneem, Ajwad Abrar
arXiv:2606. 08000v1 Announce Type: cross Abstract: The progress of large language models (LLMs) has fueled claims that model-generated summaries rival or even surpass human-written references, raising questions about whether summarization remains an open research problem.
By Dongqi Liu, Chenxi Whitehouse, Zheng Zhao, Zhuchen Cao, Jian Li, Yabiao Wang
arXiv:2610.19166v1 Announce Type: new
Abstract: Meta-evaluation of text generation metrics and LLM-judges is primarily conducted using metric-human correlations. However, prior work has shown that co...
By Anubhav Jangra, Adrian de Wynter
arXiv:2606. 27226v1 Announce Type: new Abstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug.
By Sangwoo Cho, Kushal Chawla, Pengshan Cai, Zefang Liu, Chenyang Zhu, Shi-Xiong Zhang, Sambit Sahu
Large Language Models (LLMs) are being tested as a cost‑effective alternative to human judgment for evaluating machine translation (MT). This study compares LLM agreement with human annotators on two MT quality schemes—Multidimensional Quality Metrics (MQM) and Error Span Annotation (ESA)—across 70 language pairs and public WMT23/25 data. Results show that while LLMs sometimes match or exceed human agreement, performance varies widely by scheme, language, and domain, and remains unreliable in many settings. The work also identifies specific challenges for both humans (e.g., fine‑grained MQM, low‑resource languages) and LLMs (e.g., minor errors, wrong language variants, span annotation).
By Hala Almaghout, Christian Federmann, Qin Gao
The paper introduces UPHELD, a large benchmark of human-to-human dialogues written by professional script writers, featuring realistic turn densities and over 36,000 per-turn human annotations. It evaluates existing automatic metrics and LLM-as-a-judge methods, finding them unreliable against expert human judgment. Using UPHELD, the authors develop a Mixture-of-Judges framework that improves correlation with human assessments by about 30%.
By Ilija Subasic, Andrew Rabinovich, Zhao Chen
arXiv:2606. 05494v3 Announce Type: replace-cross Abstract: Automatic text summarization has become increasingly important due to the rapid growth of digital textual information.
By Ahmed Alansary, Ali Hamdi
arXiv:2607. 21010v1 Announce Type: new Abstract: Zero-shot summarization using Large Language Models (LLMs) has significantly advanced the abstractive summarization task by producing coherent and fluent summaries.
By Vasudha Bhatnagar, Purnima Bindal, Vikas Kumar, Raj Kumari Bahl
Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. We propose BINEVAL, a framework that decomposes evaluation criteria into atomic binary questions and aggregates the resulting verdicts into interpretable, multi-dimensional scores.
arXiv:2607. 28282v1 Announce Type: cross Abstract: Evaluating the quality and relevance of textual outputs from Large Language Models (LLMs) remains challenging and resource-intensive.
By Bertil Braun, Martin Forell
PADM'E is a method for synthesizing preference‑aligned data to meta‑evaluate language‑model (LM) evaluators of agentic behaviors. It reframes meta‑evaluation as a preference judgment problem, generating criterion‑based data with small LMs and no human involvement. In a prototype, PADM'E produced 1,000 samples across four domains and three criteria, and human validation showed agreement with human judgment rising from 73% to 85% compared to a naive baseline.
By Cheng Chang, Yining Mao, Peng Qi
arXiv:2606. 05494v1 Announce Type: cross Abstract: Automatic text summarization has become increasingly important due to the rapid growth of digital textual information.
By Ahmed Alansary, Ali Hamdi