Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.16783 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918163811139584 |
|---|---|
| author | Jubair, Sheikh Omayrah, Arwa Alshammari, Amal Althnian, Alhanoof Alothaimen, Abdulhamed Alzahrani, Norah A. Alzaidi, Shahad D. Al-Twairesh, Nora Al-Thubaity, Abdulmohsen |
| author_facet | Jubair, Sheikh Omayrah, Arwa Alshammari, Amal Althnian, Alhanoof Alothaimen, Abdulhamed Alzahrani, Norah A. Alzaidi, Shahad D. Al-Twairesh, Nora Al-Thubaity, Abdulmohsen |
| contents | Recent advancements in Large Language Models (LLMs) have demonstrated sophisticated capabilities, including the ability to process and comprehend extended contexts. These emergent capabilities necessitate rigorous evaluation methods to effectively assess their performance in long-context understanding. In this paper, we present \textbf{LC-Eval}, a bilingual, multi-task evaluation benchmark designed to evaluate long-context understanding in English and Arabic, targeting context lengths ranging from 4k to over 128k tokens. LC-Eval introduces four novel and challenging tasks: multi-document question answering, bilingual question answering, claim verification within a paragraph, and multiple-choice questions based on long contexts. These tasks are designed to assess LLMs' abilities in deep reasoning, document comprehension, information tracing, and bilingual information extraction and understanding. The benchmark includes datasets in both Arabic and English for each task, allowing for a comparative analysis of their performance across different text genres. Evaluations were conducted on both open-weight and closed LLMs, with results indicating that LC-Eval presents significant challenges. Even high-performing models, such as GPT-4o, struggled with certain tasks, highlighting the complexity and rigor of the benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16783 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LC-Eval: A Bilingual Multi-Task Evaluation Benchmark for Long-Context Understanding Jubair, Sheikh Omayrah, Arwa Alshammari, Amal Althnian, Alhanoof Alothaimen, Abdulhamed Alzahrani, Norah A. Alzaidi, Shahad D. Al-Twairesh, Nora Al-Thubaity, Abdulmohsen Computation and Language Artificial Intelligence Recent advancements in Large Language Models (LLMs) have demonstrated sophisticated capabilities, including the ability to process and comprehend extended contexts. These emergent capabilities necessitate rigorous evaluation methods to effectively assess their performance in long-context understanding. In this paper, we present \textbf{LC-Eval}, a bilingual, multi-task evaluation benchmark designed to evaluate long-context understanding in English and Arabic, targeting context lengths ranging from 4k to over 128k tokens. LC-Eval introduces four novel and challenging tasks: multi-document question answering, bilingual question answering, claim verification within a paragraph, and multiple-choice questions based on long contexts. These tasks are designed to assess LLMs' abilities in deep reasoning, document comprehension, information tracing, and bilingual information extraction and understanding. The benchmark includes datasets in both Arabic and English for each task, allowing for a comparative analysis of their performance across different text genres. Evaluations were conducted on both open-weight and closed LLMs, with results indicating that LC-Eval presents significant challenges. Even high-performing models, such as GPT-4o, struggled with certain tasks, highlighting the complexity and rigor of the benchmark. |
| title | LC-Eval: A Bilingual Multi-Task Evaluation Benchmark for Long-Context Understanding |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.16783 |