English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Evaluating Large Language Models for Cross-Lingual Retrieval (arXiv 2509.14749)

Forum topic · 小凯 · 2026-07-05

Summary

This forum post discusses the arXiv paper 'Evaluating Large Language Models for Cross-Lingual Retrieval' (arXiv:2509.14749) by Longfei Zuo, Pingjun Hong, Oliver Kraus, Barbara Plank, and Robert Litschko. The work systematically evaluates large language models (LLMs) in cross-lingual information retrieval (CLIR), examining how LLM-based retrievers and rerankers compare to traditional multilingual embedding models when retrieving relevant documents across languages. The surrounding analysis frames the paper within the broader evolution of information retrieval — from BM25 and dense bi-encoders to cross-encoders, generative retrieval, and agentic search with retrieval-augmented generation (RAG). It highlights practical engineering concerns such as latency budgets, index versioning, evaluation credibility (offline nDCG vs. online satisfaction), hallucination and safety risks, and the cost of LLM inference in production search stacks. Note that the source post is largely a template entry: quantitative results, datasets, and exact experimental findings are not reproduced, so readers should consult the original PDF at arxiv.org/abs/2509.14749 for specific numbers. Related entries cover embedding model evaluation, CLIRudit for scientific documents, and cross-lingual cross-modal retrieval.

Evaluating Large Language Models for Cross-Lingual Retrieval (arXiv 2509.14749)

Paper: Evaluating Large Language Models for Cross-Lingual Retrieval Authors: Longfei Zuo, Pingjun Hong, Oliver Kraus, Barbara Plank, Robert Litschko Venue: arXiv preprint, September 2025 Topic areas: Multilingual IR, embedding models, LLM-based retrieval

> Note: The original forum post is a catalog entry built from metadata; the abstract text and quantitative results are not reproduced in the post itself. Details below reflect the paper's framing and the post's surrounding analysis. Consult the original PDF for exact experimental numbers.

Key points

  • The paper presents a systematic evaluation of large language models for cross-lingual retrieval (CLIR), positioning LLM-based retrievers/rerankers against multilingual embedding models in the modern IR stack.
  • It belongs to a growing line of work questioning whether general-purpose LLMs can replace or augment dedicated retrieval components when queries and documents span different languages.
  • The entry is indexed alongside related work on embedding model evaluation, cross-lingual retrieval of scientific documents (CLIRudit, arXiv:2504.16264), and cross-lingual cross-modal retrieval.
  • Context from the post's analysis

    Where this work sits in the IR evolution

    Neural IR has progressed from BM25 → BERT cross-encoders → dense bi-encoder retrieval → late interaction → generative retrieval and LLM agents. Each generation trades off effectiveness, efficiency, and maintainability. In the LLM era, new variables include the inference budget and the action space (whether to retrieve, how many times, which tools to call).

    Practical checklist for engineering adoption

    | Concern | Suggested practice | |---------|--------------------| | Data | PII scrubbing, partitioned indexes, rollback-capable embedding versions | | Latency | Cascaded retrieval + early stopping, query caching, async reranking | | Quality | Interleaving experiments, human audits, citation verification | | Safety | Source allowlists, poisoning detection, output filtering | | Cost | Small-model routing, distillation, hybrid sparse+dense retrieval |

    Open questions highlighted

  • Gap between offline metrics (nDCG@10, MRR, Recall@k) and online user satisfaction; LLM-as-judge still requires human cross-validation.
  • English-centric training data and unknown cross-lingual generalization.
  • Latency, cost, and hallucination risks as hard production constraints.
  • Glossary

  • IR — Information Retrieval
  • RAG — Retrieval-Augmented Generation
  • nDCG — Normalized Discounted Cumulative Gain, a ranking quality metric
  • Agentic Search — Modeling search as sequential decisions and tool calls by an LLM agent
  • Gen-IR — Generative Information Retrieval
  • Related entries

  • A Comprehensive Evaluation of Embedding Models and LLMs for IR and QA
  • CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents
  • Cl2cm: Improving Cross-Lingual Cross-Modal Retrieval
  • Cross-Lingual Cross-Modal Retrieval With Noise-Robust Fine-Tuning (IEEE)
  • Multimodal LLM Enhanced Cross-lingual Cross-modal Retrieval, MM 2024
  • The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corpora

Tags

#information-retrieval#large-language-models#cross-lingual#embedding-models#rag#evaluation-benchmarks#arxiv

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208760