System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5

• URL: http://arxiv.org/abs/2606.12392v1
• Date: Wed, 10 Jun 2026 17:54:32 GMT
• Title: System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5
• Abstract summary: We decompose the task into three subtasks: term interpretation, semantic interpretation, and emotional inference.<n>Based on multiple open-source datasets, we perform data cleansing and alignment to construct the Classical Chinese Poetry Instruction Pair dataset.<n>We then propose a domain-specialized LLM, called PoetryQwen, by applying Low-Rank Adaptation (LoRA) to fine-tune the Qwen2.5-14B model.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical poetry. However, domain-specific research on precise translation and affective-semantic understanding of classical poetry remains limited. The main challenge is that most studies treat the poetic appreciation task as a general-domain problem, neglecting the distinctive features of poetic appreciation, while high-quality and domain-specific datasets are extremely limited. To address this limitation, we decompose the task into three subtasks: term interpretation, semantic interpretation, and emotional inference. Based on multiple open-source datasets, we perform data cleansing and alignment to construct the Classical Chinese Poetry Instruction Pair Dataset (CCPoetry-49K), which comprises 49,404 high-quality instruction-response pairs explicitly optimized for this domain. We then propose a domain-specialized LLM, called PoetryQwen, by applying Low-Rank Adaptation (LoRA) to fine-tune the Qwen2.5-14B model. Experimental results on the CCL25-Eval Task 5 benchmark demonstrate that PoetryQwen achieves a score of 0.757, representing a 9.7% improvement over the Qwen2.5-14B-Instruct baseline (0.690). These findings clearly indicate that PoetryQwen significantly enhances performance in precise translation and emotional understanding of classical poetry. We present new dataset and methodological considerations intended to support the domain-specific optimization of LLMs.

Related papers

• Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features [17.99472063920348]
  We quantify the human-LLM gap along four form-level linguistic dimensions.<n>We operationalize these dimensions as five interpretable features.<n>For generation, expert evaluation on GPT-5.2 prefers feature-guided poems over the unconstrained baseline.
  arXiv  Detail & Related papers  (2026-08-29T01:45:50Z)
• Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry [45.27531384029669]
  AI-generated literary creations have raised prominent issues of creative authenticity and ethics in literary world.<n>Previous works have made significant progress in detecting AI-generated text, but it has yet to address classical Chinese poetry.<n>We introduce ChangAn, a benchmark for detecting LLM-generated classical Chinese poetry.
  arXiv  Detail & Related papers  (2026-04-11T08:52:08Z)
• PARSI: Persian Authorship Recognition via Stylometric Integration [0.0]
  We employ a multi-input neural framework to determine authorship among 67 prominent Persian poets.<n>We compiled a vast corpus of 647,653 verses of the Ganjoor digital collection, validating the data through strict preprocessing and author verification.<n>Our work focuses on the integration of deep representational forms with domain-specific features for improved authorship attribution.
  arXiv  Detail & Related papers  (2025-06-27T01:08:52Z)
• MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query [91.01970848241075]
  MERIT is the first multilingual dataset for interleaved multi-condition semantic retrieval.<n>This paper introduces MERIT, the first multilingual dataset for interleaved multi-condition semantic retrieval.
  arXiv  Detail & Related papers  (2025-06-03T17:59:14Z)
• Discourse Features Enhance Detection of Document-Level Machine-Generated Content [53.41994768824785]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation.<n>Existing MGC detectors often focus solely on surface-level information, overlooking implicit and structural features.<n>We introduce novel methodologies and datasets to overcome these challenges.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• A Bayesian Approach to Harnessing the Power of LLMs in Authorship Attribution [57.309390098903]
  Authorship attribution aims to identify the origin or author of a document. Large Language Models (LLMs) with their deep reasoning capabilities and ability to maintain long-range textual associations offer a promising alternative. Our results on the IMDb and blog datasets show an impressive 85% accuracy in one-shot authorship classification across ten authors.
  arXiv  Detail & Related papers  (2024-10-29T04:14:23Z)
• Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving [43.148203559785095]
  Large language models (LLMs) with impressive multilingual capabilities may bring a ray of hope to achieve this extreme translation demand.<n>This paper first introduces a suitable benchmark (PoetMT) where each Chinese poetry has a recognized elegant translation.<n>We propose a new metric based on GPT-4 to evaluate the extent to which current LLMs can meet these demands.
  arXiv  Detail & Related papers  (2024-08-19T12:34:31Z)
• Improving Domain Adaptation through Extended-Text Reading Comprehension [108.24709810480654]
  Recent work demonstrates that models using reading comprehension data formatted by adapting-based patterns can significantly improve performance on domain-specific tasks. However, these patterns are incapable of parsing raw corpora using domain-specific knowledge. In comparison to AdaptLLM, our method achieves an improvement exceeding 5% in domain-specific tasks.
  arXiv  Detail & Related papers  (2024-01-14T13:11:31Z)
• Non-Parametric Domain Adaptation for End-to-End Speech Translation [72.37869362559212]
  End-to-End Speech Translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency, and fewer parameters. We propose a novel non-parametric method that leverages domain-specific text translation corpus to achieve domain adaptation for the E2E-ST system.
  arXiv  Detail & Related papers  (2022-05-23T11:41:02Z)
• CCPM: A Chinese Classical Poetry Matching Dataset [50.90794811956129]
  We propose a novel task to assess a model's semantic understanding of poetry by poem matching. This task requires the model to select one line of Chinese classical poetry among four candidates according to the modern Chinese translation of a line of poetry. To construct this dataset, we first obtain a set of parallel data of Chinese classical poetry and modern Chinese translation.
  arXiv  Detail & Related papers  (2021-06-03T16:49:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.