Research Papers 论文研究 5h ago Updated 55m ago 更新于 55分钟前 43

KSE-Web: An Analysis of Hybrid Retrieval and LLM-Assisted Query Expansion for Low-Resource Khmer Semantic Search KSE-Web:低资源高棉语语义搜索的混合检索与LLM辅助查询扩展分析

KSE-Web introduces a new Khmer semantic search dataset with 3K cleaned full-text documents and 300 manually reviewed user-style queries with silver relevance labels Character n-gram BM25 achieves the strongest performance (0.943 Recall, 0.876 nDCG), outperforming multilingual dense retrieval alone Hybrid BM25+dense retrieval performs comparably to BM25 alone (0.929 Recall, 0.871 nDCG), suggesting dense models add limited value for low-resource Khmer LLM-assisted query expansion does not outperfo 针对低资源语言高棉语的语义检索挑战,构建了KSE-Web数据集(3K清洗文档、300个用户风格查询) BM25在实验中表现最优(Recall 0.943, nDCG 0.876),混合BM25+dense检索表现相当(Recall 0.929, nDCG 0.871) LLM辅助查询扩展未能超越非扩展检索,但Qwen2.5-3B显著优于Qwen2.5-0.5B,表明模型规模影响扩展质量 直接LLM扩展存在主题漂移、通用术语和噪声重构问题,简单过滤可能丢失有用语义线索

55
Hot 热度
72
Quality 质量
58
Impact 影响力

Analysis 深度分析

TL;DR

  • KSE-Web introduces a new Khmer semantic search dataset with 3K cleaned full-text documents and 300 manually reviewed user-style queries with silver relevance labels
  • Character n-gram BM25 achieves the strongest performance (0.943 Recall, 0.876 nDCG), outperforming multilingual dense retrieval alone
  • Hybrid BM25+dense retrieval performs comparably to BM25 alone (0.929 Recall, 0.871 nDCG), suggesting dense models add limited value for low-resource Khmer
  • LLM-assisted query expansion does not outperform baseline retrieval; however, Qwen2.5-3B significantly outperforms Qwen2.5-0.5B, indicating model scale matters for expansion quality
  • Direct LLM expansion introduces topic drift, generic terms, and noisy reformulations, while simple filtering risks removing useful semantic cues

Why It Matters

This work addresses a critical gap in low-resource language NLP by providing one of the first annotated Khmer search datasets and systematically evaluating retrieval strategies for a language with unique challenges like ambiguous word boundaries and mixed Khmer-English usage. For AI practitioners working with underrepresented languages, it demonstrates that simpler retrieval methods can still dominate over complex LLM-based approaches, offering practical guidance on when to invest in expensive expansion techniques versus relying on robust baseline methods.

Technical Details

  • Dataset constructed from ~17K candidate Khmer titles, filtered down to 3K cleaned full-text documents after normalization, deduplication, and document-length control; includes 300 manually reviewed user-style Khmer queries with silver relevance labels and partial human verification
  • Evaluated four retrieval approaches: character n-gram BM25, multilingual dense retrieval, hybrid BM25+dense retrieval, and LLM-assisted query expansion using Qwen2.5 models (0.5B and 3B variants)
  • BM25 achieved 0.943 Recall and 0.876 nDCG; hybrid retrieval achieved 0.929 Recall and 0.871 nDCG; dense retrieval alone performed notably lower
  • LLM expansion analysis revealed that larger models (Qwen2.5-3B) produced substantially better expanded queries than smaller ones (Qwen2.5-0.5B), but neither matched non-expanded retrieval performance
  • Identified key failure modes of LLM expansion: topic drift, introduction of generic terms, noisy reformulations, and the risk that simple filtering may discard useful semantic cues

Industry Insight

  • For low-resource language search systems, investing in robust lexical retrieval (e.g., character n-gram BM25) should be prioritized over expensive LLM-based query expansion until language-specific embedding models and larger-scale annotated datasets become available
  • When deploying LLM-assisted retrieval for underrepresented languages, model scale is a decisive factor—smaller models (sub-1B parameters) may produce insufficiently quality expansions, and careful filtering strategies are needed to avoid both topic drift and over-aggressive noise removal
  • The KSE-Web dataset and findings provide a benchmark for future Khmer-aware retrieval model development, highlighting the need for language-specific embedding models and stronger human-verified annotations to advance the field

TL;DR

  • 针对低资源语言高棉语的语义检索挑战,构建了KSE-Web数据集(3K清洗文档、300个用户风格查询)
  • BM25在实验中表现最优(Recall 0.943, nDCG 0.876),混合BM25+dense检索表现相当(Recall 0.929, nDCG 0.871)
  • LLM辅助查询扩展未能超越非扩展检索,但Qwen2.5-3B显著优于Qwen2.5-0.5B,表明模型规模影响扩展质量
  • 直接LLM扩展存在主题漂移、通用术语和噪声重构问题,简单过滤可能丢失有用语义线索

为什么值得看

本文为低资源语言语义检索提供了重要的实证分析,揭示了LLM辅助查询扩展在高棉语场景下的局限性,同时验证了传统BM25方法的有效性,对多语言检索系统设计和低资源语言NLP研究具有参考价值。

技术解析

  • 数据集构建:从约17K候选高棉语标题中筛选出3K清洗后的完整文本文档(经过过滤、标准化、去重和长度控制),包含300个手动审查的用户风格高棉语搜索查询和银标相关性标签(部分人工验证)
  • 实验方法:评估了四种检索策略——字符n-gram BM25、多语言密集检索、混合BM25+dense检索、以及使用Qwen2.5模型的LLM辅助查询扩展
  • 模型对比:使用Qwen2.5-0.5B和Qwen2.5-3B进行查询扩展实验,发现较大模型(3B)产生的扩展查询结果显著优于较小模型(0.5B)
  • 问题分析:直接LLM扩展可能引入主题漂移、通用术语和噪声重构,而简单过滤策略可能移除有用的语义线索

行业启示

  • 低资源语言检索仍需以传统方法(如BM25)为基础,LLM辅助扩展需谨慎使用,不能盲目依赖
  • 模型规模对低资源语言查询扩展效果有显著影响,应选择足够大的模型以保证扩展质量
  • 未来需要构建更强的人类验证标注数据集,并开发高棉语感知的专用检索模型以提升检索性能

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

LLM 大模型 RAG 检索增强生成 Embedding Model 嵌入模型 Dataset 数据集 Research 科学研究